diff --git a/examples/AC/AudioCaps-Test/data-00000-of-00001.arrow b/examples/AC/AudioCaps-Test/data-00000-of-00001.arrow index 7aec04f73d9fe156417abc9a21aa1d6c732b16fc..4d12c9fae95f305c95e41bdc58256b02f5f03e69 100644 --- a/examples/AC/AudioCaps-Test/data-00000-of-00001.arrow +++ b/examples/AC/AudioCaps-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f374a52ffbc12ad01d0573db305765d7b447f2d4a45590b87d9bb20aaa443d80 -size 972840 +oid sha256:763873f50c487232e2b86ab43956d6d0edfac6d112b87934e6bedac16b008bbb +size 978016 diff --git a/examples/AC/AudioCaps-Test/dataset_info.json b/examples/AC/AudioCaps-Test/dataset_info.json index c5138402a850f4b4605862059b4c7ab8debdb92b..3ace708369e9f25967c1a066010e018e988ef627 100644 --- a/examples/AC/AudioCaps-Test/dataset_info.json +++ b/examples/AC/AudioCaps-Test/dataset_info.json @@ -171,6 +171,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AC/AudioCaps-Test/sample_0.wav b/examples/AC/AudioCaps-Test/sample_0.wav index 4d69d901b51460ad829bd5c3b96bd16b4a62909e..2954d9d99c095b22309678328befe41bcb939cf2 100644 Binary files a/examples/AC/AudioCaps-Test/sample_0.wav and b/examples/AC/AudioCaps-Test/sample_0.wav differ diff --git a/examples/AC/AudioCaps-Test/sample_1.wav b/examples/AC/AudioCaps-Test/sample_1.wav index fb2163d74f884d02d085d1680e467f5fcfdb91d3..bad635baa6615c8c230a211855257af13e4a4ee6 100644 Binary files a/examples/AC/AudioCaps-Test/sample_1.wav and b/examples/AC/AudioCaps-Test/sample_1.wav differ diff --git a/examples/AC/AudioCaps-Test/sample_2.wav b/examples/AC/AudioCaps-Test/sample_2.wav index 27962998a41716585567178d244d99ad6f8684e7..b4faa2c874e56cddaf5515ce5fa21099b6b662db 100644 Binary files a/examples/AC/AudioCaps-Test/sample_2.wav and b/examples/AC/AudioCaps-Test/sample_2.wav differ diff --git a/examples/AC/AudioCaps-Test/state.json b/examples/AC/AudioCaps-Test/state.json index 014ade4c15956eca02b3b36e38274d20e16d0618..ec3bcf18171ca2b86d65ae66695480510791344d 100644 --- a/examples/AC/AudioCaps-Test/state.json +++ b/examples/AC/AudioCaps-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "7dd956b95601f713", + "_fingerprint": "7cc5b61ce18c8217", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/AC/WavCaps-Test/data-00000-of-00001.arrow b/examples/AC/WavCaps-Test/data-00000-of-00001.arrow index e8bc45db1c473357c16ab9c1effc971d920f3d54..c8c5c2298582581f3b16c2ac894f00f6ca984089 100644 --- a/examples/AC/WavCaps-Test/data-00000-of-00001.arrow +++ b/examples/AC/WavCaps-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:150d89e21ac2457a6906cc5066b9ada8ea777a8242277803fb946cbdce5489e9 -size 1221920 +oid sha256:b937b5a9fe7043c0b73ab507a45d7dbd83b8248c178ae0ce48635f18dcc1b1a1 +size 1147896 diff --git a/examples/AC/WavCaps-Test/dataset_info.json b/examples/AC/WavCaps-Test/dataset_info.json index 8ac6e1be5f6fbdee81efb2e5d107213ff13d5377..1b1895386bb88fffe8b18a11d0af692bcf64fdfb 100644 --- a/examples/AC/WavCaps-Test/dataset_info.json +++ b/examples/AC/WavCaps-Test/dataset_info.json @@ -167,6 +167,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AC/WavCaps-Test/sample_0.wav b/examples/AC/WavCaps-Test/sample_0.wav index 3ae6c0b454d470c5565fc6770051d08ca2bf693f..da8fb09d6f5992324bb82844398adb5c0647b881 100644 Binary files a/examples/AC/WavCaps-Test/sample_0.wav and b/examples/AC/WavCaps-Test/sample_0.wav differ diff --git a/examples/AC/WavCaps-Test/sample_1.wav b/examples/AC/WavCaps-Test/sample_1.wav index 0579abdb9ca1dc82c841c8024cdbd4fc5dbd0f9e..853f73f604e22d6b8c499340f6cc409e5a5fa833 100644 Binary files a/examples/AC/WavCaps-Test/sample_1.wav and b/examples/AC/WavCaps-Test/sample_1.wav differ diff --git a/examples/AC/WavCaps-Test/sample_2.wav b/examples/AC/WavCaps-Test/sample_2.wav index 4c647b74ede7e40740775fd68323fb57229d1383..aa7993b03868cc5aa35f6eb79f7b38cc6b060fec 100644 Binary files a/examples/AC/WavCaps-Test/sample_2.wav and b/examples/AC/WavCaps-Test/sample_2.wav differ diff --git a/examples/AC/WavCaps-Test/state.json b/examples/AC/WavCaps-Test/state.json index 77521aca2021217bce1aaaeb9ffca5a48285c78d..97a3a0535482739a260fcaae0d84c17112410e2e 100644 --- a/examples/AC/WavCaps-Test/state.json +++ b/examples/AC/WavCaps-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "22a6dfe54867e49c", + "_fingerprint": "c7a1810f866a86af", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow b/examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow index 717dcdea3195bf8df2c15be325436ad84575d624..a535e271c50fa09914136cfba54bfc38e42c586c 100644 --- a/examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow +++ b/examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:98001fd22061906f2d3c6713c94f33ef08e48a8fa4dfdae81abdfa7de80658f6 -size 977096 +oid sha256:90088d8d01afee2d1a7e09877083ccbc07cf654475ebbc382d45112d127e345f +size 975672 diff --git a/examples/AQA/AudioCaps-QA-Test/dataset_info.json b/examples/AQA/AudioCaps-QA-Test/dataset_info.json index a271f8f69652bbad9be548c5545f57ef7d351f0e..e00339a9d40d3fe236bf1a816f7f6cb839710d27 100644 --- a/examples/AQA/AudioCaps-QA-Test/dataset_info.json +++ b/examples/AQA/AudioCaps-QA-Test/dataset_info.json @@ -175,6 +175,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AQA/AudioCaps-QA-Test/sample_0.wav b/examples/AQA/AudioCaps-QA-Test/sample_0.wav index 21e1b511fd264d1a7659a9e513407961bf087cdb..22452da07b7d19239e9391aa03bf432e719fe47b 100644 Binary files a/examples/AQA/AudioCaps-QA-Test/sample_0.wav and b/examples/AQA/AudioCaps-QA-Test/sample_0.wav differ diff --git a/examples/AQA/AudioCaps-QA-Test/sample_1.wav b/examples/AQA/AudioCaps-QA-Test/sample_1.wav index 4c39f41dc29ac5cb08966dfdd8a73f904ddb1823..297fd9cb356b62ca2f0577a1b60e6ddfd8b8b803 100644 Binary files a/examples/AQA/AudioCaps-QA-Test/sample_1.wav and b/examples/AQA/AudioCaps-QA-Test/sample_1.wav differ diff --git a/examples/AQA/AudioCaps-QA-Test/sample_2.wav b/examples/AQA/AudioCaps-QA-Test/sample_2.wav index 35e1e28a00d6c890d2a92f65fd54f6dc6b071e97..43d2cf3a4991a6e0a663b94dd85ad3bb73322e8c 100644 Binary files a/examples/AQA/AudioCaps-QA-Test/sample_2.wav and b/examples/AQA/AudioCaps-QA-Test/sample_2.wav differ diff --git a/examples/AQA/AudioCaps-QA-Test/state.json b/examples/AQA/AudioCaps-QA-Test/state.json index d8870c294493bc158c42378391238a63e792d3b6..66c46ae1a1d9ad7405a9370f733cc3be9f49f69d 100644 --- a/examples/AQA/AudioCaps-QA-Test/state.json +++ b/examples/AQA/AudioCaps-QA-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "60b01046f3ad5343", + "_fingerprint": "15709330a46e2556", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow b/examples/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow index 8ece8019ead9d050e03de2b21ac40ba33ef6c018..b0b4bb257b03f1d4c3d32d3fcdc2321e1f339f05 100644 --- a/examples/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow +++ b/examples/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3dc4022c4dff1427b545e9890aa4fdcbfa3017b1b101ca4c366f52715ca57e7d -size 1735400 +oid sha256:e945510b58f71cc98abe3021507a565a2dc1c01cc709ba68371b8ec91dd47211 +size 1931856 diff --git a/examples/AQA/Clotho-AQA-Test/dataset_info.json b/examples/AQA/Clotho-AQA-Test/dataset_info.json index 6c56b97992cd0d890362752b2624919a9de2a1ee..c40944441a79522271969c50c971bf55c0c93651 100644 --- a/examples/AQA/Clotho-AQA-Test/dataset_info.json +++ b/examples/AQA/Clotho-AQA-Test/dataset_info.json @@ -158,6 +158,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AQA/Clotho-AQA-Test/sample_0.wav b/examples/AQA/Clotho-AQA-Test/sample_0.wav index f5f0a048306163ed4345c00aadeae8426b9d797a..3a215d4c9dc306b5d92e23a65e83578eba2fbdf7 100644 Binary files a/examples/AQA/Clotho-AQA-Test/sample_0.wav and b/examples/AQA/Clotho-AQA-Test/sample_0.wav differ diff --git a/examples/AQA/Clotho-AQA-Test/sample_1.wav b/examples/AQA/Clotho-AQA-Test/sample_1.wav index e1d918453e30499c4e72944444dcbc7b91919383..697e97c7a67dba2b38b1627addc573fa04b4f42b 100644 Binary files a/examples/AQA/Clotho-AQA-Test/sample_1.wav and b/examples/AQA/Clotho-AQA-Test/sample_1.wav differ diff --git a/examples/AQA/Clotho-AQA-Test/sample_2.wav b/examples/AQA/Clotho-AQA-Test/sample_2.wav index a62fd4ca863efed677bdde085e94389031fcdbf4..c850d74f729f55632c3add760f85cb80167ae4c8 100644 Binary files a/examples/AQA/Clotho-AQA-Test/sample_2.wav and b/examples/AQA/Clotho-AQA-Test/sample_2.wav differ diff --git a/examples/AQA/Clotho-AQA-Test/state.json b/examples/AQA/Clotho-AQA-Test/state.json index 4283473fd35325b09ea63487bc79660b9bfd8083..4a8562c7822390b8e9644bc5273030809fbde7d6 100644 --- a/examples/AQA/Clotho-AQA-Test/state.json +++ b/examples/AQA/Clotho-AQA-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "9728812a68aca05b", + "_fingerprint": "185dd63ad411b41a", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow b/examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow index 126d54db4d30af711a2e8d1f91ac2e86fb839faa..d3cff815a4872ca8aa240221e34c0a624bf5e95f 100644 --- a/examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow +++ b/examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7c724e98a1d3d280ee37873a4580f4784796e523172424c0a5fa9db5551ed60f -size 954704 +oid sha256:39abfb31fd73770062a8b9a5cc57f3ed7240d0154a66907060c5ff1485ab627a +size 1170696 diff --git a/examples/AQA/WavCaps-QA-Test/dataset_info.json b/examples/AQA/WavCaps-QA-Test/dataset_info.json index aa59daad62b54e79ee3ad8bb220dcef211f82c84..0bd828964785c21ebc61d23afea93a0b1aa6feb9 100644 --- a/examples/AQA/WavCaps-QA-Test/dataset_info.json +++ b/examples/AQA/WavCaps-QA-Test/dataset_info.json @@ -171,6 +171,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AQA/WavCaps-QA-Test/sample_0.wav b/examples/AQA/WavCaps-QA-Test/sample_0.wav index ed90d471475217726db780c39603232512bf3785..b0b1ac328a6d3456f8b4fa6928c52d681d6479e9 100644 Binary files a/examples/AQA/WavCaps-QA-Test/sample_0.wav and b/examples/AQA/WavCaps-QA-Test/sample_0.wav differ diff --git a/examples/AQA/WavCaps-QA-Test/sample_1.wav b/examples/AQA/WavCaps-QA-Test/sample_1.wav index 9882a2cca41a0736468480868d4a2a41de7ededb..6c936d73839c8fa80ac1e96fb8c684bcf171aaff 100644 Binary files a/examples/AQA/WavCaps-QA-Test/sample_1.wav and b/examples/AQA/WavCaps-QA-Test/sample_1.wav differ diff --git a/examples/AQA/WavCaps-QA-Test/sample_2.wav b/examples/AQA/WavCaps-QA-Test/sample_2.wav index 36983956624f0737ac2cb3da85677cfd5d530e54..88ebea1a1609bb64fc4675338ec13b8f634f7c4f 100644 Binary files a/examples/AQA/WavCaps-QA-Test/sample_2.wav and b/examples/AQA/WavCaps-QA-Test/sample_2.wav differ diff --git a/examples/AQA/WavCaps-QA-Test/state.json b/examples/AQA/WavCaps-QA-Test/state.json index caa4e1e8d47964acfec8a4601e6cc62cfa0cd9e0..b488a972d81343d9f057f9f9c5c87458d7800a4a 100644 --- a/examples/AQA/WavCaps-QA-Test/state.json +++ b/examples/AQA/WavCaps-QA-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "2b00ba42b5d66bed", + "_fingerprint": "5aa9e7145a7a79a7", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow b/examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow index 521f220a8ad758da13b15cf1207ca1d56019c410..2dde523d1262daaaf133ec1035e5a9fddd75b724 100644 --- a/examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow +++ b/examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:378d8cf14e6cf16ca63841ef7833b021b65c81f95dc093abac169ecb030ebb0a -size 1213568 +oid sha256:f3f331d20df4468c1de4b688040b20da929fa2c5cce04ca633ef78aa986019ed +size 568296 diff --git a/examples/AR/VoxCeleb-Accent-Test/dataset_info.json b/examples/AR/VoxCeleb-Accent-Test/dataset_info.json index 91b217e4844573d2e3a2d0072b2276b37723047c..328995ed278d8242ea9ba476f8b8d4b4096e6ff1 100644 --- a/examples/AR/VoxCeleb-Accent-Test/dataset_info.json +++ b/examples/AR/VoxCeleb-Accent-Test/dataset_info.json @@ -179,6 +179,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/AR/VoxCeleb-Accent-Test/sample_0.wav b/examples/AR/VoxCeleb-Accent-Test/sample_0.wav index 430d0d31ed6af0e3d219b84402902587aacfd716..498a70b813aaacdfb91e9788641fedc2ba09b80f 100644 Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_0.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_0.wav differ diff --git a/examples/AR/VoxCeleb-Accent-Test/sample_1.wav b/examples/AR/VoxCeleb-Accent-Test/sample_1.wav index c13b7c8d4d9189f4a6ce7b106e9c5419f0e06352..8e180a13f5299da1b61e5d259967111e5b13ce73 100644 Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_1.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_1.wav differ diff --git a/examples/AR/VoxCeleb-Accent-Test/sample_2.wav b/examples/AR/VoxCeleb-Accent-Test/sample_2.wav index cb33b1aabb60d6150a60e2f3c296c184bba786ac..1a85cf143ce3e92a42d973291c14c9a2526ee914 100644 Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_2.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_2.wav differ diff --git a/examples/AR/VoxCeleb-Accent-Test/state.json b/examples/AR/VoxCeleb-Accent-Test/state.json index 1a799ec15938c1058eb0d2806c8d2125c6d64cd6..60c8ded950ba1b95550dd3c5b21f9c97ccbdea5d 100644 --- a/examples/AR/VoxCeleb-Accent-Test/state.json +++ b/examples/AR/VoxCeleb-Accent-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "8e8e0515e988a016", + "_fingerprint": "196da8d0b0da0eb9", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow b/examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow index 3c64ebed9243ab13ed4112031125c9ca02ace6a2..58f7a687d87bebd9495a7546eaf75d85f5ad251b 100644 --- a/examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:63619af0016e2250bd7196654e0e3ce15a5b4d4d524829e2b0eb23f5de67fce2 -size 734592 +oid sha256:fa4ac44c57ee33e1af6bd0246b9c9e4f53074c1cbab4178ed6777cc2313f3dcf +size 451128 diff --git a/examples/ASR/Common-Voice-15-En-Test/dataset_info.json b/examples/ASR/Common-Voice-15-En-Test/dataset_info.json index 532307de6238db4f6c7e9d7084dc690a975d8920..8cb5c5961365a9592b3a752a87003f4857fbd273 100644 --- a/examples/ASR/Common-Voice-15-En-Test/dataset_info.json +++ b/examples/ASR/Common-Voice-15-En-Test/dataset_info.json @@ -38,7 +38,7 @@ "_type": "Value" }, "age": { - "dtype": "null", + "dtype": "string", "_type": "Value" }, "client_id": { @@ -199,6 +199,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Common-Voice-15-En-Test/sample_0.wav b/examples/ASR/Common-Voice-15-En-Test/sample_0.wav index d1259db1843cdd79bc9a3bb4778067fd209a65f3..fb9976b0a2e9ee58c8f1728809acc745e8bc2288 100644 Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_0.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_0.wav differ diff --git a/examples/ASR/Common-Voice-15-En-Test/sample_1.wav b/examples/ASR/Common-Voice-15-En-Test/sample_1.wav index 2b2a7d92a7ec2749ba9ef870edc34c5b5fc99ed0..a417c9ba3e7569551650ea6c7b0b07b0baf163b3 100644 Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_1.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_1.wav differ diff --git a/examples/ASR/Common-Voice-15-En-Test/sample_2.wav b/examples/ASR/Common-Voice-15-En-Test/sample_2.wav index 7f5ceed8701b8ba50e59431c5e9f7b95ed7c1727..620c78eeba9db18388b5cd9c0ee1e2aa45467854 100644 Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_2.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_2.wav differ diff --git a/examples/ASR/Common-Voice-15-En-Test/state.json b/examples/ASR/Common-Voice-15-En-Test/state.json index 22446de8f160a7d55b4ac6835a39fd0c0fffb62c..16f711f341a571e713d1f5306643092199bcdfbc 100644 --- a/examples/ASR/Common-Voice-15-En-Test/state.json +++ b/examples/ASR/Common-Voice-15-En-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "23bec5037b5ce6a4", + "_fingerprint": "c8a3251745f6df7c", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Earnings21-Test/data-00000-of-00001.arrow b/examples/ASR/Earnings21-Test/data-00000-of-00001.arrow index 9c10b6cdcd155433a916ee1ad952e6a4e5a16bb9..dd231e9ad1e5d65754dbf3b50872d4d1dde2842c 100644 --- a/examples/ASR/Earnings21-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Earnings21-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bc0f66d55bb0faeadc7193c43aa71ea56431335340f30303e2cb25c9b2a79744 -size 367003808 +oid sha256:cfd427c50cf1fafd3147e1bfdbbb93175d5df932e5f77af611ffb4a91a7e98a0 +size 278500120 diff --git a/examples/ASR/Earnings21-Test/dataset_info.json b/examples/ASR/Earnings21-Test/dataset_info.json index 83b8d9f868f8dda4f2f055e065c0e23ebbdc4734..2be7d1a6997fc6b32d2f431f21dea593696c8f5b 100644 --- a/examples/ASR/Earnings21-Test/dataset_info.json +++ b/examples/ASR/Earnings21-Test/dataset_info.json @@ -163,6 +163,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Earnings21-Test/sample_0.wav b/examples/ASR/Earnings21-Test/sample_0.wav index 39ae668314a511d89d654992908b84760b40efd2..17ba2bbd1608c96c62a420bd267cf9270da8f035 100644 --- a/examples/ASR/Earnings21-Test/sample_0.wav +++ b/examples/ASR/Earnings21-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8276aa4b4bd55749772152b8c7adf6fe558ad8e4f26624504612d72c3760fffa -size 81919596 +oid sha256:607725d2a33f206a0f00668f1907f4d997fc7dbe7d1e1f9c82045496412bd8bd +size 115039268 diff --git a/examples/ASR/Earnings21-Test/sample_1.wav b/examples/ASR/Earnings21-Test/sample_1.wav index c8ca1696c117ec01d3a742ca6ea5a48042288b55..c306304487d6f70aee07421b5d8074fda883d82c 100644 --- a/examples/ASR/Earnings21-Test/sample_1.wav +++ b/examples/ASR/Earnings21-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8a57a2bcbf2a7df4da219a0233b66326e1e5225bc6719f596775a01fe2a87ba8 -size 138517676 +oid sha256:db092ee918b48e37b79b079e2de667d127c0008293a0309be1c6a16a4840b820 +size 46016300 diff --git a/examples/ASR/Earnings21-Test/sample_2.wav b/examples/ASR/Earnings21-Test/sample_2.wav index 61397a47ae54eb428c7702d53649005438bae9bd..883786553b129c58cb1b844deb18f918aae31242 100644 --- a/examples/ASR/Earnings21-Test/sample_2.wav +++ b/examples/ASR/Earnings21-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c1b4a765dcbb96ca99ddbc01224a4f36d66bad376beb7e04f7a8a4964c02a46a -size 144361004 +oid sha256:05be7627a44d69a191edf323e032deff28d35764c2c7ea283ec10dacc0f125bc +size 115040418 diff --git a/examples/ASR/Earnings21-Test/state.json b/examples/ASR/Earnings21-Test/state.json index cf8c9f552b4bb777dc628a2cf84b39eb0a86a964..af746199db5dd9a1317ae09ae736d19f92612dd8 100644 --- a/examples/ASR/Earnings21-Test/state.json +++ b/examples/ASR/Earnings21-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "6d8e11ac5a63a2d2", + "_fingerprint": "fee62a469e646020", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Earnings22-Test/data-00000-of-00001.arrow b/examples/ASR/Earnings22-Test/data-00000-of-00001.arrow index 50e2b79aa719907dcf6d81b810c16503f59bd2c0..ccfb2e3c3df744eb70092cead339367fd2e95606 100644 --- a/examples/ASR/Earnings22-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Earnings22-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:46d31942482d6db16028f7690fc0bfe00321da1b00fe6357040bf392d9ecd2f1 -size 333814624 +oid sha256:5af58666f15916a33082740b0f78f5fd1442af151393786dc3bba031ca2c9975 +size 310182408 diff --git a/examples/ASR/Earnings22-Test/dataset_info.json b/examples/ASR/Earnings22-Test/dataset_info.json index 1bf27e3aaa89f2fa43812252ac2377fab8ae1708..2be7d1a6997fc6b32d2f431f21dea593696c8f5b 100644 --- a/examples/ASR/Earnings22-Test/dataset_info.json +++ b/examples/ASR/Earnings22-Test/dataset_info.json @@ -92,6 +92,24 @@ "_type": "Value" } }, + "meralion_audiollm_v1_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, "whisper_large_v3_with_llama_3_8b_instruct": { "answer": { "dtype": "string", @@ -145,6 +163,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Earnings22-Test/sample_0.wav b/examples/ASR/Earnings22-Test/sample_0.wav index e630bf409bf71fe86b572d2681802566a0c26d39..b308b1e538e115c7be7cca0459d689fcc4617e38 100644 --- a/examples/ASR/Earnings22-Test/sample_0.wav +++ b/examples/ASR/Earnings22-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d17808f5da0d8a7ecefeaa914e5be18186dd1735523c9a4a6e1738bf3cfc77e5 -size 152305196 +oid sha256:157806533e87a01bbe3d165939e5c07ef0ae088e320779c47e0248733b649f05 +size 86494508 diff --git a/examples/ASR/Earnings22-Test/sample_1.wav b/examples/ASR/Earnings22-Test/sample_1.wav index 5a74e84d2d502a40842368c1b8120c1b64126eac..c35bf8e13f7bf6798ca66bce6213a1a1cd9e2150 100644 --- a/examples/ASR/Earnings22-Test/sample_1.wav +++ b/examples/ASR/Earnings22-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ec1b0aada93420d121572445d6e300df9037249dba2df85a81f16533759b29eb -size 85850534 +oid sha256:6e700f2424bece3124a29935392465976dbf1b5818fdf281d09069ad20dc45f4 +size 136868396 diff --git a/examples/ASR/Earnings22-Test/sample_2.wav b/examples/ASR/Earnings22-Test/sample_2.wav index 721687e4d2ac3d2062818facf1256ee9acdcb280..22c2b227701a38511f21e886fc1f99d16d7ef90b 100644 --- a/examples/ASR/Earnings22-Test/sample_2.wav +++ b/examples/ASR/Earnings22-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e5022646a7ea99298c8b02f6589c9d3943cf3649e337ad4a1579e40a7dcd3b33 -size 94064684 +oid sha256:0e89cc70492e8edda7322212c60946cb9fd4f5e246542bc806e3406f06873ef3 +size 84602924 diff --git a/examples/ASR/Earnings22-Test/state.json b/examples/ASR/Earnings22-Test/state.json index ae076d2547c5302d7bfe3408a69af25738b0730e..ca1ceecfac4bb6ce9019feaba8f79aef43264535 100644 --- a/examples/ASR/Earnings22-Test/state.json +++ b/examples/ASR/Earnings22-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "f71b90ac0caefff8", + "_fingerprint": "c7f7dfbe71f40f5a", "_format_columns": [ "context", "instruction", @@ -13,9 +13,12 @@ "salmonn_7b", "wavllm_fairseq", "Qwen2-Audio-7B-Instruct", + "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/GigaSpeech-Test/data-00000-of-00001.arrow b/examples/ASR/GigaSpeech-Test/data-00000-of-00001.arrow index 0ed825009d02f0dc8e0ba110a51fb0038a27ffc8..5c90cc176c427017ba1caa7908cd22a1a25721b7 100644 --- a/examples/ASR/GigaSpeech-Test/data-00000-of-00001.arrow +++ b/examples/ASR/GigaSpeech-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d24f90d8303622d11e227e0149a726a9a06dcad84ff5deb89cb20ff2289482b0 -size 670440 +oid sha256:4b0917870f66f4f7157272a115e09b23f04c59574facb6224a65e1b8105e51b1 +size 550744 diff --git a/examples/ASR/GigaSpeech-Test/dataset_info.json b/examples/ASR/GigaSpeech-Test/dataset_info.json index 4a71f4f719892bbe1f5c71332420787fe5dc92fe..ced1f7e4e80340a8dca22a50df7b84a4bc3c838d 100644 --- a/examples/ASR/GigaSpeech-Test/dataset_info.json +++ b/examples/ASR/GigaSpeech-Test/dataset_info.json @@ -191,6 +191,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/GigaSpeech-Test/sample_0.wav b/examples/ASR/GigaSpeech-Test/sample_0.wav index f08bbdf0a0af40f77b8c73c44976c63a78d2fc39..5ebece2fc765f43e53eaa5864162ce970936a698 100644 Binary files a/examples/ASR/GigaSpeech-Test/sample_0.wav and b/examples/ASR/GigaSpeech-Test/sample_0.wav differ diff --git a/examples/ASR/GigaSpeech-Test/sample_1.wav b/examples/ASR/GigaSpeech-Test/sample_1.wav index 62d149d28202bbf67bc52cf39c3c87da9e934a4c..4e94917fdffe914e777ca8f8a3dd9d040cf34aad 100644 Binary files a/examples/ASR/GigaSpeech-Test/sample_1.wav and b/examples/ASR/GigaSpeech-Test/sample_1.wav differ diff --git a/examples/ASR/GigaSpeech-Test/sample_2.wav b/examples/ASR/GigaSpeech-Test/sample_2.wav index 3ce3d6a5694f07d04ab17fde1e29f308312e5517..8eb65ce641d25e434b2573dfefa9358d6b5d99b3 100644 Binary files a/examples/ASR/GigaSpeech-Test/sample_2.wav and b/examples/ASR/GigaSpeech-Test/sample_2.wav differ diff --git a/examples/ASR/GigaSpeech-Test/state.json b/examples/ASR/GigaSpeech-Test/state.json index 8fca1d869d122159c4afa7b0214a240abe2f382d..c0ae9e2877e81f05ad620b7c7a8d3b26c2ef321f 100644 --- a/examples/ASR/GigaSpeech-Test/state.json +++ b/examples/ASR/GigaSpeech-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "67d1ab1b99556a9f", + "_fingerprint": "749a511e2cc30275", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/IMDA-Part1-ASR-Test/data-00000-of-00001.arrow b/examples/ASR/IMDA-Part1-ASR-Test/data-00000-of-00001.arrow index 343ae9ac8e6b6002920c3e4731c14c2d7a22ab77..77a53de53a13079ea4e3c8c7bb9edaee7a5ad7f6 100644 --- a/examples/ASR/IMDA-Part1-ASR-Test/data-00000-of-00001.arrow +++ b/examples/ASR/IMDA-Part1-ASR-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9b70a131a1075b0729e4e29e03bc3ce0d3406a84cc1e7b3f1329891149687cfb -size 445576 +oid sha256:b71a70d034b58f737c17c004e391679667ab3ab0e5eb11680ca44a3ca4433f07 +size 728424 diff --git a/examples/ASR/IMDA-Part1-ASR-Test/dataset_info.json b/examples/ASR/IMDA-Part1-ASR-Test/dataset_info.json index ede02d74b595679e2a6f3b2256ab4c69e535f09e..3429feeca42f04ae8fceef6d26bd6b3d89343edf 100644 --- a/examples/ASR/IMDA-Part1-ASR-Test/dataset_info.json +++ b/examples/ASR/IMDA-Part1-ASR-Test/dataset_info.json @@ -193,6 +193,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav b/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav index 37142cc04ab5d70e5c1a3f00c48c5555c1b44b31..31bc48a843ad9333925257d1cc3000c2a5a4cae9 100644 Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav differ diff --git a/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav b/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav index d66fd5602e0d455844807ef1f2a176aaaee1610b..28f620cbae23bbef0bf8fb46b3f4be3525395778 100644 Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav differ diff --git a/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav b/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav index dc6701f3abb29f0fc5957697385ecc4a7d6c740b..90ce16e327723936003c00d471a091c420f5ab0a 100644 Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav differ diff --git a/examples/ASR/IMDA-Part1-ASR-Test/state.json b/examples/ASR/IMDA-Part1-ASR-Test/state.json index 7c287183cce740341697c42ff3ca2cb4344caddf..f11e7467b0d5d88047372718cc7b1424f4de7135 100644 --- a/examples/ASR/IMDA-Part1-ASR-Test/state.json +++ b/examples/ASR/IMDA-Part1-ASR-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "6de71e0f4c76af43", + "_fingerprint": "9419619e05bfc9dc", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/IMDA-Part2-ASR-Test/data-00000-of-00001.arrow b/examples/ASR/IMDA-Part2-ASR-Test/data-00000-of-00001.arrow index 8b1ccb41fde7b391d58735d4e315bf9a51d3835a..de1004ceea810bd853c4b42c65d944abdb183394 100644 --- a/examples/ASR/IMDA-Part2-ASR-Test/data-00000-of-00001.arrow +++ b/examples/ASR/IMDA-Part2-ASR-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ff2dab78b2f99f296e7164af2595d76e3d055c156549b4e56d4de3dd24e56c90 -size 316456 +oid sha256:10ffd231941e615c6e67ea1e8032584599b77a1277acc115d046ad4da13225c6 +size 464952 diff --git a/examples/ASR/IMDA-Part2-ASR-Test/dataset_info.json b/examples/ASR/IMDA-Part2-ASR-Test/dataset_info.json index ede02d74b595679e2a6f3b2256ab4c69e535f09e..3429feeca42f04ae8fceef6d26bd6b3d89343edf 100644 --- a/examples/ASR/IMDA-Part2-ASR-Test/dataset_info.json +++ b/examples/ASR/IMDA-Part2-ASR-Test/dataset_info.json @@ -193,6 +193,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav b/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav index e49eb3e417896071b646badc40adc4b92f6b99da..9ceb6cf708a8740569744dd7570425f08ff6bd96 100644 Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav differ diff --git a/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav b/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav index 56cd23b4ba9c56fd053ae80c292ea8aa93e92293..5d2bb8c6f31811196b2bc3853530eae08a5155c9 100644 Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav differ diff --git a/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav b/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav index e1d594ef2f027e10f0bc02ffb197a5129fc3fbe7..b25ddb42137a2bcdedd2f813821e71b77ef67b6e 100644 Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav differ diff --git a/examples/ASR/IMDA-Part2-ASR-Test/state.json b/examples/ASR/IMDA-Part2-ASR-Test/state.json index 9e63a4d63533a0a5fd894966479ccc22f2528377..2d7dc93c71beab172bdb00e01b9d5658db19074e 100644 --- a/examples/ASR/IMDA-Part2-ASR-Test/state.json +++ b/examples/ASR/IMDA-Part2-ASR-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "58564e4bc21961b9", + "_fingerprint": "c0f2d01dcb22f4b6", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/LibriSpeech-Test-Clean/data-00000-of-00001.arrow b/examples/ASR/LibriSpeech-Test-Clean/data-00000-of-00001.arrow index eaf91b2e98a654896139a7f3429aa7d63a6052ad..b78c0651c247db1f2e4aa94bd38b7a29b29ec99b 100644 --- a/examples/ASR/LibriSpeech-Test-Clean/data-00000-of-00001.arrow +++ b/examples/ASR/LibriSpeech-Test-Clean/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6d8400ec1502f226dd9f82fac53b5f3d8360fffaf859b3b56fb854157ac75580 -size 638008 +oid sha256:2b30dce427d9dbdcdff16114333b6d9e5c610b3ccfaa8f685194ab3d6d2873a1 +size 980600 diff --git a/examples/ASR/LibriSpeech-Test-Clean/dataset_info.json b/examples/ASR/LibriSpeech-Test-Clean/dataset_info.json index 43a7d2a02a5e9b58fc92641d1fa33f66bbb3ffb8..601f6f9fbd1e138a40453ec7da4c8e4313cfab8b 100644 --- a/examples/ASR/LibriSpeech-Test-Clean/dataset_info.json +++ b/examples/ASR/LibriSpeech-Test-Clean/dataset_info.json @@ -175,6 +175,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav b/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav index 07a99e97bf2b54b1c4028cf9280ec6cae995adb8..249fd3e0bfafe96b8952556b80be99181fefb2a0 100644 Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav b/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav index 9bc645b1dd32cc7e4be13999d3bb3190d6559376..e6c2c7c9670c6e1d345db668d70ca077f3f6cf0b 100644 Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav b/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav index b6d879dd4e7dc07638f71ca0808f7c9395efb420..0b19024a7e72eb47a17113e9a2fca56ea08b07b3 100644 Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Clean/state.json b/examples/ASR/LibriSpeech-Test-Clean/state.json index 3f21062dca2ac77c037dd729833f9e181bcffd92..7ab1d8011db4c2335979f01d2f439bb31c889d16 100644 --- a/examples/ASR/LibriSpeech-Test-Clean/state.json +++ b/examples/ASR/LibriSpeech-Test-Clean/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "5f41ed9e62814ad1", + "_fingerprint": "e836cc656a13dcac", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/LibriSpeech-Test-Other/data-00000-of-00001.arrow b/examples/ASR/LibriSpeech-Test-Other/data-00000-of-00001.arrow index 41472f0ea104954c43203897429ad80fdcccc688..3a06a9cc7639240b114593894b1c3a3cc81de524 100644 --- a/examples/ASR/LibriSpeech-Test-Other/data-00000-of-00001.arrow +++ b/examples/ASR/LibriSpeech-Test-Other/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3c5fede20b21cb95627071cce4e51da3efd9c695fbf605db431da96b220ed081 -size 490816 +oid sha256:d9122c85b419c35da0b8d54daa3048fa75a41d84e1e0c649645073d46fc99698 +size 718904 diff --git a/examples/ASR/LibriSpeech-Test-Other/dataset_info.json b/examples/ASR/LibriSpeech-Test-Other/dataset_info.json index 43a7d2a02a5e9b58fc92641d1fa33f66bbb3ffb8..601f6f9fbd1e138a40453ec7da4c8e4313cfab8b 100644 --- a/examples/ASR/LibriSpeech-Test-Other/dataset_info.json +++ b/examples/ASR/LibriSpeech-Test-Other/dataset_info.json @@ -175,6 +175,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/LibriSpeech-Test-Other/sample_0.wav b/examples/ASR/LibriSpeech-Test-Other/sample_0.wav index f0d20ff28c7910013946cc22d27bc14b642a397c..2afaf29c9403ce6c8719bd02f4d7ff3ac478ddfd 100644 Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_0.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_0.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Other/sample_1.wav b/examples/ASR/LibriSpeech-Test-Other/sample_1.wav index 6faf2b05a1da557f1039edf9b67f714ab51c4bed..68cffa4d8a794dfd7c4b5ceedeb60b2899e63727 100644 Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_1.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_1.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Other/sample_2.wav b/examples/ASR/LibriSpeech-Test-Other/sample_2.wav index 20fb0bcad6556cfca16b1bf5466d1755061c631a..d577336924f3e3e6512617e090814f4ea908db4c 100644 Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_2.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_2.wav differ diff --git a/examples/ASR/LibriSpeech-Test-Other/state.json b/examples/ASR/LibriSpeech-Test-Other/state.json index bd657759ba4398444807dfcc3134ccd9d1bb79f8..f172220479d27e7a9e390b3ca96a6fa8688c6233 100644 --- a/examples/ASR/LibriSpeech-Test-Other/state.json +++ b/examples/ASR/LibriSpeech-Test-Other/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "cdae4114b2fdba28", + "_fingerprint": "03b7f6480e5a4f48", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Peoples-Speech-Test/data-00000-of-00001.arrow b/examples/ASR/Peoples-Speech-Test/data-00000-of-00001.arrow index a15c777f5e033628e063edf6af6ccf6c171869bc..573b07f8d20bf38da645cf9bda023e8ca2257623 100644 --- a/examples/ASR/Peoples-Speech-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Peoples-Speech-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7380189d307b0bfd90a24bc66224cb1d7fef1a2561670b907e78004dd59e9675 -size 946072 +oid sha256:ce24e3afe7b50a6940ed70214b381798f24c4f293ca3818582e7b21a7c45a391 +size 825808 diff --git a/examples/ASR/Peoples-Speech-Test/dataset_info.json b/examples/ASR/Peoples-Speech-Test/dataset_info.json index 726c69526174b236cc38180a6b27905c9b182714..17e177d72c504a484d0c8efed3bde699629764ff 100644 --- a/examples/ASR/Peoples-Speech-Test/dataset_info.json +++ b/examples/ASR/Peoples-Speech-Test/dataset_info.json @@ -167,6 +167,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Peoples-Speech-Test/sample_0.wav b/examples/ASR/Peoples-Speech-Test/sample_0.wav index 272fccbc0970764c68d7927c25d39ce307b484c1..6ee444a802dac427207b7cf09acaa69806706a13 100644 Binary files a/examples/ASR/Peoples-Speech-Test/sample_0.wav and b/examples/ASR/Peoples-Speech-Test/sample_0.wav differ diff --git a/examples/ASR/Peoples-Speech-Test/sample_1.wav b/examples/ASR/Peoples-Speech-Test/sample_1.wav index 99f1c35821539e7cf65c0ece46d29ac8f137fbd7..18a0f0a92fcae6853cde4b5ad75eb94079942363 100644 Binary files a/examples/ASR/Peoples-Speech-Test/sample_1.wav and b/examples/ASR/Peoples-Speech-Test/sample_1.wav differ diff --git a/examples/ASR/Peoples-Speech-Test/sample_2.wav b/examples/ASR/Peoples-Speech-Test/sample_2.wav index d9572909c9ffdc4d725b589d351ade4b0aa2998b..829d3c5ddcac7c7444ece7e5ec2ca2c2699e09fd 100644 Binary files a/examples/ASR/Peoples-Speech-Test/sample_2.wav and b/examples/ASR/Peoples-Speech-Test/sample_2.wav differ diff --git a/examples/ASR/Peoples-Speech-Test/state.json b/examples/ASR/Peoples-Speech-Test/state.json index 61144ef80bc11b38566cc904feca7995f1ab162c..de53035dc660657d2474001ed99085e87c03a9eb 100644 --- a/examples/ASR/Peoples-Speech-Test/state.json +++ b/examples/ASR/Peoples-Speech-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "a31e8115b04802d9", + "_fingerprint": "a55271f9b22843a3", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Tedlium3-Long-form-Test/data-00000-of-00001.arrow b/examples/ASR/Tedlium3-Long-form-Test/data-00000-of-00001.arrow index 663557dcadf2e292e0aef28df0003fd1c4aa6430..b4df3c4666d348885097d39c2d203d146f68a6e7 100644 --- a/examples/ASR/Tedlium3-Long-form-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Tedlium3-Long-form-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7fae0d1b2077588d2333f81d62d8b4aff7ddbdd84c2770d068c4274b4932b1bf -size 94387448 +oid sha256:62e77b7972898cddc5105dff3bc1cf821cb958553a09293c47ffb9f0639555b9 +size 69807560 diff --git a/examples/ASR/Tedlium3-Long-form-Test/dataset_info.json b/examples/ASR/Tedlium3-Long-form-Test/dataset_info.json index 10047f79d2f1a1b8a3f0185fa89ecb0170a4d82c..bbea49ee7735a48550e0f3ca242cbd0933146ef2 100644 --- a/examples/ASR/Tedlium3-Long-form-Test/dataset_info.json +++ b/examples/ASR/Tedlium3-Long-form-Test/dataset_info.json @@ -175,6 +175,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Tedlium3-Long-form-Test/sample_0.wav b/examples/ASR/Tedlium3-Long-form-Test/sample_0.wav index 2eff19f1f7ce5c124d20e874f244975410f7113c..458550d1f8ba2439a49bbdd3acce6d28a8050798 100644 --- a/examples/ASR/Tedlium3-Long-form-Test/sample_0.wav +++ b/examples/ASR/Tedlium3-Long-form-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:32c1ab4c6363f3db0f5fca8bdc5f2eb780522a08da3cd00bf6a4b1ea7e3cc0f8 -size 37362604 +oid sha256:df373978edb883e7c38cdb99f293ab770f71a63bc44214185751e229d53edc4c +size 31435404 diff --git a/examples/ASR/Tedlium3-Long-form-Test/sample_1.wav b/examples/ASR/Tedlium3-Long-form-Test/sample_1.wav index a218d274caefb6e72dcdf1ef14639eca3d92c54c..ab9204d8220ac39f77a16c6caa4a5c2205b5299d 100644 --- a/examples/ASR/Tedlium3-Long-form-Test/sample_1.wav +++ b/examples/ASR/Tedlium3-Long-form-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb2d7db63f67644b5a8883727929c9f2e96631c45900321734aa020589ade4c5 -size 29474026 +oid sha256:2e6bb9d4e01b093db26d317deb1578c337d56d5672dd8aa5fcb1e231752d222e +size 10910764 diff --git a/examples/ASR/Tedlium3-Long-form-Test/state.json b/examples/ASR/Tedlium3-Long-form-Test/state.json index 802648bca0c3237cf834eb90ae139e55941d4e34..03d0b299297b548c57131c52fd1b0a20f3ca9d34 100644 --- a/examples/ASR/Tedlium3-Long-form-Test/state.json +++ b/examples/ASR/Tedlium3-Long-form-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "58eff5b352a6c4af", + "_fingerprint": "1717f426f4d53a70", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ASR/Tedlium3-Test/data-00000-of-00001.arrow b/examples/ASR/Tedlium3-Test/data-00000-of-00001.arrow index 37faafbdb7e866e84dc5ab62fc6e79e51ee85ae1..e53ec6662d0dfeb36cbd608c3361a8b815c5a2c4 100644 --- a/examples/ASR/Tedlium3-Test/data-00000-of-00001.arrow +++ b/examples/ASR/Tedlium3-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:85722f6b2cedad0e78d58b44bae464bad6828555dd239e13758b4002dbc47277 -size 779144 +oid sha256:b53b08072d013fa81f7ebb737865676555e31baf850fc71988bcbf87e6d74f42 +size 855184 diff --git a/examples/ASR/Tedlium3-Test/dataset_info.json b/examples/ASR/Tedlium3-Test/dataset_info.json index 10047f79d2f1a1b8a3f0185fa89ecb0170a4d82c..bbea49ee7735a48550e0f3ca242cbd0933146ef2 100644 --- a/examples/ASR/Tedlium3-Test/dataset_info.json +++ b/examples/ASR/Tedlium3-Test/dataset_info.json @@ -175,6 +175,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ASR/Tedlium3-Test/sample_0.wav b/examples/ASR/Tedlium3-Test/sample_0.wav index b8aea73a6c3619a9b9044110a1f8a6d98613724a..5c3ded7eabf45f4a142311c57c0cacd2e4c2f15f 100644 Binary files a/examples/ASR/Tedlium3-Test/sample_0.wav and b/examples/ASR/Tedlium3-Test/sample_0.wav differ diff --git a/examples/ASR/Tedlium3-Test/sample_1.wav b/examples/ASR/Tedlium3-Test/sample_1.wav index 5d0764a8f20943f4bb99690206c17dfff7985307..80c9daf6fbc95f4a06285450d6957a3fa0f08ba3 100644 Binary files a/examples/ASR/Tedlium3-Test/sample_1.wav and b/examples/ASR/Tedlium3-Test/sample_1.wav differ diff --git a/examples/ASR/Tedlium3-Test/sample_2.wav b/examples/ASR/Tedlium3-Test/sample_2.wav index 1a4418fb82d58a63b8d6658a096b619913bb614d..09da0382ff58be7a74ce0133a642d51887fbd7ac 100644 Binary files a/examples/ASR/Tedlium3-Test/sample_2.wav and b/examples/ASR/Tedlium3-Test/sample_2.wav differ diff --git a/examples/ASR/Tedlium3-Test/state.json b/examples/ASR/Tedlium3-Test/state.json index 05687cd786f8e6e1ceb43737d38165b6602b7dc9..2e60a052ff263e41001c995a3bd4b609b8cab2e4 100644 --- a/examples/ASR/Tedlium3-Test/state.json +++ b/examples/ASR/Tedlium3-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "564760102352a6d3", + "_fingerprint": "dc7c3b308d9d7ab2", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/data-00000-of-00001.arrow b/examples/CNASR/Aishell-ASR-ZH-Test/data-00000-of-00001.arrow index 759ddab5ac1222d92dda592d8dc030cd78b47d73..41c7f57c374954eb72f459f8c4899bb065b8eec8 100644 --- a/examples/CNASR/Aishell-ASR-ZH-Test/data-00000-of-00001.arrow +++ b/examples/CNASR/Aishell-ASR-ZH-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4da460a2c54c584f866c17ff3c2922180da4674e31cd0ff2381b1416ccea8672 -size 458328 +oid sha256:6e94a2fc0eefa6d750019fde22dd5160f9764623ce01dc6ea00cd5eda50720fa +size 605360 diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/dataset_info.json b/examples/CNASR/Aishell-ASR-ZH-Test/dataset_info.json index c42d75c27c529687386dbb50124a3b199bd3b176..5904f10ae8b9ba12cd4990e4b0a0b78a6c35ef88 100644 --- a/examples/CNASR/Aishell-ASR-ZH-Test/dataset_info.json +++ b/examples/CNASR/Aishell-ASR-ZH-Test/dataset_info.json @@ -155,6 +155,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/sample_0.wav b/examples/CNASR/Aishell-ASR-ZH-Test/sample_0.wav index 0631f9745cbc39d30899c534252b902cb0c33ba0..fa12295d2bfeaf3313a03de991e25d6396b1ea91 100644 Binary files a/examples/CNASR/Aishell-ASR-ZH-Test/sample_0.wav and b/examples/CNASR/Aishell-ASR-ZH-Test/sample_0.wav differ diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/sample_1.wav b/examples/CNASR/Aishell-ASR-ZH-Test/sample_1.wav index 23da00fdc805d70ec90066b602512d110280554d..3f413224d5cd58c42853152b6a2d6f4fecbdedaf 100644 Binary files a/examples/CNASR/Aishell-ASR-ZH-Test/sample_1.wav and b/examples/CNASR/Aishell-ASR-ZH-Test/sample_1.wav differ diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/sample_2.wav b/examples/CNASR/Aishell-ASR-ZH-Test/sample_2.wav index 7d4f68158ad3c22144160b44d2b94dd2489a4f4d..69e9ddf2e43e09f6adde70d7f040a780e332748d 100644 Binary files a/examples/CNASR/Aishell-ASR-ZH-Test/sample_2.wav and b/examples/CNASR/Aishell-ASR-ZH-Test/sample_2.wav differ diff --git a/examples/CNASR/Aishell-ASR-ZH-Test/state.json b/examples/CNASR/Aishell-ASR-ZH-Test/state.json index 72520f06a2dfd1a4c01b59451d2c6ebb5cbf7868..3fef1b89479ee29a76fe0a5ed2db27174426e62e 100644 --- a/examples/CNASR/Aishell-ASR-ZH-Test/state.json +++ b/examples/CNASR/Aishell-ASR-ZH-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "c55bbfbc80134880", + "_fingerprint": "3935151f419dac34", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ER/IEMOCAP-Emotion-Test/data-00000-of-00001.arrow b/examples/ER/IEMOCAP-Emotion-Test/data-00000-of-00001.arrow index 1830ee319657fddd5b9dc6afb1cb56ca5aed08a7..5300eaef44f5538cbb8bd48c3fcf2c1ae1fa6744 100644 --- a/examples/ER/IEMOCAP-Emotion-Test/data-00000-of-00001.arrow +++ b/examples/ER/IEMOCAP-Emotion-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f1c10a21b55a9a758bd1ff39ac8cf3833285016c6ff6c171296ac2a981bde2dd -size 549984 +oid sha256:74fd1357d494dac861b0aa1677f6d8e8eda477b336cc1264c25fb6ce95a2eba7 +size 910472 diff --git a/examples/ER/IEMOCAP-Emotion-Test/dataset_info.json b/examples/ER/IEMOCAP-Emotion-Test/dataset_info.json index ec9982ce23f02e4a30ed69b54c9da27522206ad7..14ff4e720a72477e10f15ea6088774542065142f 100644 --- a/examples/ER/IEMOCAP-Emotion-Test/dataset_info.json +++ b/examples/ER/IEMOCAP-Emotion-Test/dataset_info.json @@ -179,6 +179,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ER/IEMOCAP-Emotion-Test/sample_0.wav b/examples/ER/IEMOCAP-Emotion-Test/sample_0.wav index 69f31212a1bf5d0220e889032a34835cc4f8414b..6e78416a9484a8da0d6318f363594ef015d7f32f 100644 Binary files a/examples/ER/IEMOCAP-Emotion-Test/sample_0.wav and b/examples/ER/IEMOCAP-Emotion-Test/sample_0.wav differ diff --git a/examples/ER/IEMOCAP-Emotion-Test/sample_1.wav b/examples/ER/IEMOCAP-Emotion-Test/sample_1.wav index f8c1d3734b3687c8a2205aad61368bffa54cadf2..273dce98582758ab45c63a4829da9528ad048b56 100644 Binary files a/examples/ER/IEMOCAP-Emotion-Test/sample_1.wav and b/examples/ER/IEMOCAP-Emotion-Test/sample_1.wav differ diff --git a/examples/ER/IEMOCAP-Emotion-Test/sample_2.wav b/examples/ER/IEMOCAP-Emotion-Test/sample_2.wav index 12e93e96005e4c422ed6f789bf1ac0273e6fc483..6b47fcac54d72d0a9eddad1b9e3ce10492df51c9 100644 Binary files a/examples/ER/IEMOCAP-Emotion-Test/sample_2.wav and b/examples/ER/IEMOCAP-Emotion-Test/sample_2.wav differ diff --git a/examples/ER/IEMOCAP-Emotion-Test/state.json b/examples/ER/IEMOCAP-Emotion-Test/state.json index 47aac6246491fd600c3ee9f77d9ece88074be1e1..290ed0050fb90e6f5eecd797c9265df0d4ae408c 100644 --- a/examples/ER/IEMOCAP-Emotion-Test/state.json +++ b/examples/ER/IEMOCAP-Emotion-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "e76359f2b84e8913", + "_fingerprint": "c05a58257683ad44", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ER/MELD-Emotion-Test/data-00000-of-00001.arrow b/examples/ER/MELD-Emotion-Test/data-00000-of-00001.arrow index 696725cbba34fa35029967897648879fd58c05b5..63346c48f4b7c7571bf12e875ae6a8cb9c05d328 100644 --- a/examples/ER/MELD-Emotion-Test/data-00000-of-00001.arrow +++ b/examples/ER/MELD-Emotion-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f90c18d98e82805348d2c55e1c957e9ec94cfe977f0193322cf04b1eb090a818 -size 435464 +oid sha256:e8e5e4afb9b63e2a5f53492c5ca5f76de1b2a2a618e01902e3b09723b7bed88a +size 222688 diff --git a/examples/ER/MELD-Emotion-Test/dataset_info.json b/examples/ER/MELD-Emotion-Test/dataset_info.json index 4452de7db0b48a7e233a40373a253c8d4cca6984..8501bee4b00d1a02b2714377c03abaf2ecfabe3d 100644 --- a/examples/ER/MELD-Emotion-Test/dataset_info.json +++ b/examples/ER/MELD-Emotion-Test/dataset_info.json @@ -195,6 +195,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ER/MELD-Emotion-Test/sample_0.wav b/examples/ER/MELD-Emotion-Test/sample_0.wav index ae16f804b90a7eeabb027d788c1b7e291a50405f..b585c132092d4f00815d2d044d19fb8753fffb1c 100644 Binary files a/examples/ER/MELD-Emotion-Test/sample_0.wav and b/examples/ER/MELD-Emotion-Test/sample_0.wav differ diff --git a/examples/ER/MELD-Emotion-Test/sample_1.wav b/examples/ER/MELD-Emotion-Test/sample_1.wav index 621748fea89f2ae2cb00ccf4c5bc60722757966c..1a1e95054f9a0888bb91404b1a77a11bb7cd2db6 100644 Binary files a/examples/ER/MELD-Emotion-Test/sample_1.wav and b/examples/ER/MELD-Emotion-Test/sample_1.wav differ diff --git a/examples/ER/MELD-Emotion-Test/sample_2.wav b/examples/ER/MELD-Emotion-Test/sample_2.wav index 389dfb97dbb804a09de0bf8f007f59be149eb2c8..74c7347ed820c22804a5e08895100b1c269a1ec9 100644 Binary files a/examples/ER/MELD-Emotion-Test/sample_2.wav and b/examples/ER/MELD-Emotion-Test/sample_2.wav differ diff --git a/examples/ER/MELD-Emotion-Test/state.json b/examples/ER/MELD-Emotion-Test/state.json index 176649fbdd530cb7834be5416a7c4810f251679a..a43e0b70ed8e6eeb3f93d3e14b31b1481004bd7e 100644 --- a/examples/ER/MELD-Emotion-Test/state.json +++ b/examples/ER/MELD-Emotion-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "af1e1756291ebf0e", + "_fingerprint": "f3f84dd864023b5b", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ER/MELD-Sentiment-Test/data-00000-of-00001.arrow b/examples/ER/MELD-Sentiment-Test/data-00000-of-00001.arrow index d61f1e0e2139e636ce349dba968fb539be883d1e..6157d0cc71b55ad116134535ccae6c1513a6bc64 100644 --- a/examples/ER/MELD-Sentiment-Test/data-00000-of-00001.arrow +++ b/examples/ER/MELD-Sentiment-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:92fb7fe8450dd0779a51b115355d40fc9e827e843be92f791e95a189c956f988 -size 205056 +oid sha256:d5393e254e03127d5adfd74bfb4fa9fdf3743681c3b05fa25f8a6387c1bc3540 +size 313096 diff --git a/examples/ER/MELD-Sentiment-Test/dataset_info.json b/examples/ER/MELD-Sentiment-Test/dataset_info.json index 4452de7db0b48a7e233a40373a253c8d4cca6984..8501bee4b00d1a02b2714377c03abaf2ecfabe3d 100644 --- a/examples/ER/MELD-Sentiment-Test/dataset_info.json +++ b/examples/ER/MELD-Sentiment-Test/dataset_info.json @@ -195,6 +195,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ER/MELD-Sentiment-Test/sample_0.wav b/examples/ER/MELD-Sentiment-Test/sample_0.wav index 34c3f4a45a3e8ed05f716b36d0770ec367449f4d..21a5139f712830072656b3174ca5e44594a3e6ee 100644 Binary files a/examples/ER/MELD-Sentiment-Test/sample_0.wav and b/examples/ER/MELD-Sentiment-Test/sample_0.wav differ diff --git a/examples/ER/MELD-Sentiment-Test/sample_1.wav b/examples/ER/MELD-Sentiment-Test/sample_1.wav index aa2cd17de168f8dc8c16081cfb5cf2567c7a8701..615fa8ec070c39b5d911b24b7661e5777b0215f9 100644 Binary files a/examples/ER/MELD-Sentiment-Test/sample_1.wav and b/examples/ER/MELD-Sentiment-Test/sample_1.wav differ diff --git a/examples/ER/MELD-Sentiment-Test/sample_2.wav b/examples/ER/MELD-Sentiment-Test/sample_2.wav index 99a6b96db3614af9fc6b3fc25800ceed3df78bb3..8c6f3ad946657c08ec114c4650b160d6136610a9 100644 Binary files a/examples/ER/MELD-Sentiment-Test/sample_2.wav and b/examples/ER/MELD-Sentiment-Test/sample_2.wav differ diff --git a/examples/ER/MELD-Sentiment-Test/state.json b/examples/ER/MELD-Sentiment-Test/state.json index 803fbcc33947edac767d6061118da9cb6318c792..8c0d8df00ccaf954596f5d7ca25486a7f27b8fbf 100644 --- a/examples/ER/MELD-Sentiment-Test/state.json +++ b/examples/ER/MELD-Sentiment-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "7785c7413a306461", + "_fingerprint": "08571196c2ccc4a1", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/GR/IEMOCAP-Gender-Test/data-00000-of-00001.arrow b/examples/GR/IEMOCAP-Gender-Test/data-00000-of-00001.arrow index 9565d6bf740c6b2cf101ed6305208a8384a91b14..bfaf0c0faae5d0a6d9eef419f2b533061adb1b45 100644 --- a/examples/GR/IEMOCAP-Gender-Test/data-00000-of-00001.arrow +++ b/examples/GR/IEMOCAP-Gender-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c8a9d624ae7d40b7e7a024e67478150837531b368f9f9f34b4e396d2881af059 -size 431064 +oid sha256:d84bb85072597c996dc065206616082b6de413e9cd3e0467fb580d19f6eb639c +size 399016 diff --git a/examples/GR/IEMOCAP-Gender-Test/dataset_info.json b/examples/GR/IEMOCAP-Gender-Test/dataset_info.json index ec9982ce23f02e4a30ed69b54c9da27522206ad7..14ff4e720a72477e10f15ea6088774542065142f 100644 --- a/examples/GR/IEMOCAP-Gender-Test/dataset_info.json +++ b/examples/GR/IEMOCAP-Gender-Test/dataset_info.json @@ -179,6 +179,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/GR/IEMOCAP-Gender-Test/sample_0.wav b/examples/GR/IEMOCAP-Gender-Test/sample_0.wav index f052a2e401793a6a2cad7fd12ec9e7dc305ea5b2..ada3ffddc533d331356aab0069f041868f1c2d92 100644 Binary files a/examples/GR/IEMOCAP-Gender-Test/sample_0.wav and b/examples/GR/IEMOCAP-Gender-Test/sample_0.wav differ diff --git a/examples/GR/IEMOCAP-Gender-Test/sample_1.wav b/examples/GR/IEMOCAP-Gender-Test/sample_1.wav index fa42b5bdbf1f708fcb039e99845040df41d84da4..fc456e23585aaa12bea9d8bc482acb191874b39f 100644 Binary files a/examples/GR/IEMOCAP-Gender-Test/sample_1.wav and b/examples/GR/IEMOCAP-Gender-Test/sample_1.wav differ diff --git a/examples/GR/IEMOCAP-Gender-Test/sample_2.wav b/examples/GR/IEMOCAP-Gender-Test/sample_2.wav index 5f81af300bee9be5ef0de8ab0c7e120a4d0b917b..9f3a7037ec7c07af7faeaccb768bc4c6d7e65af4 100644 Binary files a/examples/GR/IEMOCAP-Gender-Test/sample_2.wav and b/examples/GR/IEMOCAP-Gender-Test/sample_2.wav differ diff --git a/examples/GR/IEMOCAP-Gender-Test/state.json b/examples/GR/IEMOCAP-Gender-Test/state.json index ed84f0cd8521cebcc00f6456b76bc9d78d767f38..9555943df4bc815cf1c991a242b72ba978d27778 100644 --- a/examples/GR/IEMOCAP-Gender-Test/state.json +++ b/examples/GR/IEMOCAP-Gender-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "339f506943f7e884", + "_fingerprint": "119a3dc50d4e5c9d", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/GR/VoxCeleb-Gender-Test/data-00000-of-00001.arrow b/examples/GR/VoxCeleb-Gender-Test/data-00000-of-00001.arrow index cd2247677be4407d4033f79be586c6763f82a2fa..402e75356b1611cbf8192a56f1c59c69fb4abe64 100644 --- a/examples/GR/VoxCeleb-Gender-Test/data-00000-of-00001.arrow +++ b/examples/GR/VoxCeleb-Gender-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:850b8dff1601e9d93b3c6f7d02d35b0865f26da47d953dfb912cc2d62eca4d55 -size 517400 +oid sha256:e2281d8530ad8ee776a43f156bad2b4e6c76028b7abb596bac40c10b34f85e86 +size 1077672 diff --git a/examples/GR/VoxCeleb-Gender-Test/dataset_info.json b/examples/GR/VoxCeleb-Gender-Test/dataset_info.json index 91b217e4844573d2e3a2d0072b2276b37723047c..328995ed278d8242ea9ba476f8b8d4b4096e6ff1 100644 --- a/examples/GR/VoxCeleb-Gender-Test/dataset_info.json +++ b/examples/GR/VoxCeleb-Gender-Test/dataset_info.json @@ -179,6 +179,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/GR/VoxCeleb-Gender-Test/sample_0.wav b/examples/GR/VoxCeleb-Gender-Test/sample_0.wav index 1108051bf59741d780dd1895721cef626655ad4d..05b34faf75956d69f9cb14419dfeeab137ddbf23 100644 Binary files a/examples/GR/VoxCeleb-Gender-Test/sample_0.wav and b/examples/GR/VoxCeleb-Gender-Test/sample_0.wav differ diff --git a/examples/GR/VoxCeleb-Gender-Test/sample_1.wav b/examples/GR/VoxCeleb-Gender-Test/sample_1.wav index 170de49b786e11c8d6f9ea105f30cef9eceb5862..be3f8cc502c2db3a937e493a4d619ffa5d18507d 100644 Binary files a/examples/GR/VoxCeleb-Gender-Test/sample_1.wav and b/examples/GR/VoxCeleb-Gender-Test/sample_1.wav differ diff --git a/examples/GR/VoxCeleb-Gender-Test/sample_2.wav b/examples/GR/VoxCeleb-Gender-Test/sample_2.wav index b520f722b1880dc2c15fb2090a174016982e9eff..62c0d73b2c07d6cae573be5864f6589fd82de905 100644 Binary files a/examples/GR/VoxCeleb-Gender-Test/sample_2.wav and b/examples/GR/VoxCeleb-Gender-Test/sample_2.wav differ diff --git a/examples/GR/VoxCeleb-Gender-Test/state.json b/examples/GR/VoxCeleb-Gender-Test/state.json index 59877853a608c9f52a3b29cf3f9db4524b1addce..1d44e1b16f528ea86aaea9a619f4f69970425906 100644 --- a/examples/GR/VoxCeleb-Gender-Test/state.json +++ b/examples/GR/VoxCeleb-Gender-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "d16ef5cdce6dd4c2", + "_fingerprint": "1118ce5ba26f7ef5", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SI/ALPACA-Audio-Test/data-00000-of-00001.arrow b/examples/SI/ALPACA-Audio-Test/data-00000-of-00001.arrow index 1accfadab38a5c4af77efd77d5ff5336afc76126..f1a907ec55ae398ab57d229b36a1b7cf1bd810e4 100644 --- a/examples/SI/ALPACA-Audio-Test/data-00000-of-00001.arrow +++ b/examples/SI/ALPACA-Audio-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0ed7346f8dc284a9900db47ddaaae252e0145aa23dfa3ab5336fbf7c9f2d8346 -size 400680 +oid sha256:7d51a5ca65264c4c8ba9305fe09115aeae5f6ad3413dc3ec2a7b63131f4cc940 +size 474712 diff --git a/examples/SI/ALPACA-Audio-Test/dataset_info.json b/examples/SI/ALPACA-Audio-Test/dataset_info.json index 408aaad5f7e22888fd0fa1ac9c64f759cf6d77bd..16eb551319a909a2094482e1b688de8a667a034d 100644 --- a/examples/SI/ALPACA-Audio-Test/dataset_info.json +++ b/examples/SI/ALPACA-Audio-Test/dataset_info.json @@ -191,6 +191,50 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "audio_text_instruction": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "audio_text_instruction": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SI/ALPACA-Audio-Test/sample_0.wav b/examples/SI/ALPACA-Audio-Test/sample_0.wav index 39211d1c195a9613197680da766e2f46e1b7deb5..916722a9ca7666bf5ef063ac8175d4a6f740f6ee 100644 Binary files a/examples/SI/ALPACA-Audio-Test/sample_0.wav and b/examples/SI/ALPACA-Audio-Test/sample_0.wav differ diff --git a/examples/SI/ALPACA-Audio-Test/sample_1.wav b/examples/SI/ALPACA-Audio-Test/sample_1.wav index e22fc1b4899053c55b2c93f61a17ae04290603dd..aedd56715c1f0fdc331cfc1e11550b70d05c122f 100644 Binary files a/examples/SI/ALPACA-Audio-Test/sample_1.wav and b/examples/SI/ALPACA-Audio-Test/sample_1.wav differ diff --git a/examples/SI/ALPACA-Audio-Test/sample_2.wav b/examples/SI/ALPACA-Audio-Test/sample_2.wav index f61f6006c97c647388826d1ecc9dde7f2e8a8c2f..fb6cf62a9e715c159bd490c863e59a6d5cfe6b65 100644 Binary files a/examples/SI/ALPACA-Audio-Test/sample_2.wav and b/examples/SI/ALPACA-Audio-Test/sample_2.wav differ diff --git a/examples/SI/ALPACA-Audio-Test/state.json b/examples/SI/ALPACA-Audio-Test/state.json index 3bd9c038b001c84bbd46e26df7c121a7ea8e1315..73b1948c0cbb779717d459f3708ff8cf8ac39135 100644 --- a/examples/SI/ALPACA-Audio-Test/state.json +++ b/examples/SI/ALPACA-Audio-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "41ebac7aa5808e92", + "_fingerprint": "8efe6575a5935254", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SI/OpenHermes-Audio-Test/data-00000-of-00001.arrow b/examples/SI/OpenHermes-Audio-Test/data-00000-of-00001.arrow index dfcf87a518efbd9ab701363db34a83336cce8922..836e7d558fca805a9828faf855d2d17ec3491324 100644 --- a/examples/SI/OpenHermes-Audio-Test/data-00000-of-00001.arrow +++ b/examples/SI/OpenHermes-Audio-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cf78046f1beb5c172249e9692bbec2e4ce37ecfd96d6e7984aa2f8516316b061 -size 358552 +oid sha256:2c07d79b331a7ad6062445401693a6e61b3ff3f9bfbe435c1e97f49cf7b155ce +size 331824 diff --git a/examples/SI/OpenHermes-Audio-Test/dataset_info.json b/examples/SI/OpenHermes-Audio-Test/dataset_info.json index c047f4a40521a5ca6dd80262091713a20934eee1..3fcb0ec637942f4244bfa7fcf2ff8fd0bcc53bbb 100644 --- a/examples/SI/OpenHermes-Audio-Test/dataset_info.json +++ b/examples/SI/OpenHermes-Audio-Test/dataset_info.json @@ -203,6 +203,50 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "audio_text_instruction": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "audio_text_instruction": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SI/OpenHermes-Audio-Test/sample_0.wav b/examples/SI/OpenHermes-Audio-Test/sample_0.wav index fc6251969fc752f60c52056c83739e8b206578ea..f2d8572e54eeabe52f6e37c3d285d5b1a39060e6 100644 Binary files a/examples/SI/OpenHermes-Audio-Test/sample_0.wav and b/examples/SI/OpenHermes-Audio-Test/sample_0.wav differ diff --git a/examples/SI/OpenHermes-Audio-Test/sample_1.wav b/examples/SI/OpenHermes-Audio-Test/sample_1.wav index c64f49698924ca6c035902b254cabfd6015cf6f7..d937128e1c69048dab752f7ef7eca01d2bcfaf40 100644 Binary files a/examples/SI/OpenHermes-Audio-Test/sample_1.wav and b/examples/SI/OpenHermes-Audio-Test/sample_1.wav differ diff --git a/examples/SI/OpenHermes-Audio-Test/sample_2.wav b/examples/SI/OpenHermes-Audio-Test/sample_2.wav index 8086c0e0a6b16c63cc8fa165089a3cc45e65e6e3..ab627c8b8df5680d75ef24f031447af134af26c7 100644 Binary files a/examples/SI/OpenHermes-Audio-Test/sample_2.wav and b/examples/SI/OpenHermes-Audio-Test/sample_2.wav differ diff --git a/examples/SI/OpenHermes-Audio-Test/state.json b/examples/SI/OpenHermes-Audio-Test/state.json index fe7dccc553f7fd6116624ea9dd30fc50e026c50a..110fdeff43c0846cb6247b30313836dc59d25517 100644 --- a/examples/SI/OpenHermes-Audio-Test/state.json +++ b/examples/SI/OpenHermes-Audio-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "ec1d0f482d452867", + "_fingerprint": "d61111af290e69aa", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/data-00000-of-00001.arrow b/examples/SQA/CN-College-Listen-MCQ-Test/data-00000-of-00001.arrow index fe2a76df0110f305cac0f247824a2f80fe1b9921..a5043777a7263ab589cf5ec7b6ef6c3bfbc2b3d4 100644 --- a/examples/SQA/CN-College-Listen-MCQ-Test/data-00000-of-00001.arrow +++ b/examples/SQA/CN-College-Listen-MCQ-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:105fa5bf62671eaceea2e79ecb95d0d2f911bb0b6e034d7fbb94c2e6af0f4fc7 -size 1315864 +oid sha256:753bf54085e506bf7e266924d9960a5e16376879a32a489fc2bb12c632527f0d +size 1157864 diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/dataset_info.json b/examples/SQA/CN-College-Listen-MCQ-Test/dataset_info.json index 4771b4afa178372d926d8585373b25efe7c24093..1944b3cf3a58be72b3d6a9a1f4e0ac589aa5e420 100644 --- a/examples/SQA/CN-College-Listen-MCQ-Test/dataset_info.json +++ b/examples/SQA/CN-College-Listen-MCQ-Test/dataset_info.json @@ -171,6 +171,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/sample_0.wav b/examples/SQA/CN-College-Listen-MCQ-Test/sample_0.wav index 78afc269eab7bbaedde6c651ba9b0a80117893e6..a8e07e0232e347433582d0e0d4274ff6d06b2d6d 100644 --- a/examples/SQA/CN-College-Listen-MCQ-Test/sample_0.wav +++ b/examples/SQA/CN-College-Listen-MCQ-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8b8dff3a6dfd3f7841ad4ab275fabc97879ebda7530bdfb07c335d3f3b785efb -size 369138 +oid sha256:b6f03ce38ea60befe497185d393357e971d511bbf7805dbea865390d2d18498e +size 312294 diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/sample_1.wav b/examples/SQA/CN-College-Listen-MCQ-Test/sample_1.wav index 2950fb2efc80385a38eafaf8e5323e235dc6ef5a..e48947d0ec77270c19031cbd95cd509aadcb3b66 100644 Binary files a/examples/SQA/CN-College-Listen-MCQ-Test/sample_1.wav and b/examples/SQA/CN-College-Listen-MCQ-Test/sample_1.wav differ diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/sample_2.wav b/examples/SQA/CN-College-Listen-MCQ-Test/sample_2.wav index 8e38a92819daf71488f83afff75446fafa16653f..f0074f8601bbcb95d03f047522809b8cd2457e2a 100644 Binary files a/examples/SQA/CN-College-Listen-MCQ-Test/sample_2.wav and b/examples/SQA/CN-College-Listen-MCQ-Test/sample_2.wav differ diff --git a/examples/SQA/CN-College-Listen-MCQ-Test/state.json b/examples/SQA/CN-College-Listen-MCQ-Test/state.json index 209d66d20de4ced39cf612551d829563dd12715c..1f045a1707b1b0be11299af82d62d0478e339e70 100644 --- a/examples/SQA/CN-College-Listen-MCQ-Test/state.json +++ b/examples/SQA/CN-College-Listen-MCQ-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "d6665c93899c985b", + "_fingerprint": "c29bfc3c67d3e8c9", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/data-00000-of-00001.arrow b/examples/SQA/DREAM-TTS-MCQ-Test/data-00000-of-00001.arrow index e56610034a86dde6caecb02baf61a5c8e9679099..6d3d76dca62abef850d23ba25e1801017805b582 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/data-00000-of-00001.arrow +++ b/examples/SQA/DREAM-TTS-MCQ-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf928d4caee9289ce3f57f0c15aa654a86ffb341a5e95c56182fb4a7f88cf330 -size 1982432 +oid sha256:df8c989198176946679c373f63e5bc5fa25aa937a135e67bf260e3dc71278b50 +size 3215976 diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/dataset_info.json b/examples/SQA/DREAM-TTS-MCQ-Test/dataset_info.json index 1e091c2cd9b8341f9d611e06e1ae03d1ce1f1524..939c6df14af5d549f371242df35542769fc0c7f3 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/dataset_info.json +++ b/examples/SQA/DREAM-TTS-MCQ-Test/dataset_info.json @@ -167,6 +167,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/sample_0.wav b/examples/SQA/DREAM-TTS-MCQ-Test/sample_0.wav index 1b02057e2dcce381d2c274bff02eefc3641b5277..603c1c2f437a1ed54bf617f0820a846cac1ebec4 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/sample_0.wav +++ b/examples/SQA/DREAM-TTS-MCQ-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:922ec67bb0b3e8afab2222a1060101cd7103700863127a77d9f67aa09d9ae162 -size 403266 +oid sha256:55719eac3b2a1d388fbf91002a4d82b59b2b1d3f2ea2bb91a3ca7e5d5a23364f +size 318594 diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/sample_1.wav b/examples/SQA/DREAM-TTS-MCQ-Test/sample_1.wav index 8ffc084d780c4f8ed4b5401dd1c373a29fa21834..85f0332edba8f4280dcb09b99a8eed579f6331c9 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/sample_1.wav +++ b/examples/SQA/DREAM-TTS-MCQ-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5e9d0dc98dc1bbae99e0aa27f773910c40b14b2ba973378f6580d210e5e11d1b -size 1340120 +oid sha256:75047e683b9c94fc518619842605722c0a8c0d1bcb95d3113e521aed1648d887 +size 2379288 diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/sample_2.wav b/examples/SQA/DREAM-TTS-MCQ-Test/sample_2.wav index 0c392067385b635cd401aca11b0ab1c40206dcaf..ecb6d9253e63007331a76cbcfb1c583c83463850 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/sample_2.wav +++ b/examples/SQA/DREAM-TTS-MCQ-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a9f56e4d56f5384e968cd7be064056fb3039f6c5fea2cc9cb24155b1914385ab -size 225708 +oid sha256:3f8f24cda5448c255777358a3d384469f56777238fb9271f05b24d638226b0e7 +size 497858 diff --git a/examples/SQA/DREAM-TTS-MCQ-Test/state.json b/examples/SQA/DREAM-TTS-MCQ-Test/state.json index 93713a14d71ecaaf7a461735519e8172057aaa74..864cb0dfdf4ddd59f260478b0b9ce8d08908ec96 100644 --- a/examples/SQA/DREAM-TTS-MCQ-Test/state.json +++ b/examples/SQA/DREAM-TTS-MCQ-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "aa689dcb170b0cb8", + "_fingerprint": "d217927f5d54cf04", "_format_columns": [ "answer", "context", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SQA/Public-SG-Speech-QA-Test/data-00000-of-00001.arrow b/examples/SQA/Public-SG-Speech-QA-Test/data-00000-of-00001.arrow index eaf658cce0723c6d74acdf89e74dab71c772c87d..f3251e7acdff7dc3928f7493de6f79ef2dee77f0 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/data-00000-of-00001.arrow +++ b/examples/SQA/Public-SG-Speech-QA-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0f873a0cc4f7e5c1cfb6d39f055b240d3db2dc6de0e16d5132327fd9c9fb684f -size 4337968 +oid sha256:759199d0896a3c319b350af6a642f7d6280ddf31114753f7377491bfb1ce54b5 +size 3548464 diff --git a/examples/SQA/Public-SG-Speech-QA-Test/dataset_info.json b/examples/SQA/Public-SG-Speech-QA-Test/dataset_info.json index 203817254af5fa6bd621c9a43dfaaf6d61ad4922..3176bb0f42218d9924f0b399173436ec6c724be6 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/dataset_info.json +++ b/examples/SQA/Public-SG-Speech-QA-Test/dataset_info.json @@ -161,6 +161,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SQA/Public-SG-Speech-QA-Test/sample_0.wav b/examples/SQA/Public-SG-Speech-QA-Test/sample_0.wav index a7f47bc0a68166d38f958a1cc884dcd2342c98f6..04c73abe40670983982d96b2279f29a57ce2b641 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/sample_0.wav +++ b/examples/SQA/Public-SG-Speech-QA-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9d1d958bf731fbddd5078588014e3bb8c7cd1fe8744267aef62c6b5220cb1b93 -size 1120356 +oid sha256:4f98960fa7c52007952cd4e3d3f307f19391c875d6510d7f6cb774c3d4f2d9cf +size 831582 diff --git a/examples/SQA/Public-SG-Speech-QA-Test/sample_1.wav b/examples/SQA/Public-SG-Speech-QA-Test/sample_1.wav index e03c1449caeea8580f557d651d28eb079ded9884..0ec0e0c34dcc1a371223494f0819bb786a5858e1 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/sample_1.wav +++ b/examples/SQA/Public-SG-Speech-QA-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fca54dcb4dcd6a5285211d2f772b24543612d03bcf199e783140d1439f49b2f1 -size 1515128 +oid sha256:0e500a1b92d64cae3b2969d1d1d4ab2dd0b8726969a52f51bc76b0353dbf7dc7 +size 1103648 diff --git a/examples/SQA/Public-SG-Speech-QA-Test/sample_2.wav b/examples/SQA/Public-SG-Speech-QA-Test/sample_2.wav index d99371b71f61db6a6cf7ab4f134eee04bd6b979f..2a080b9469b0f04c6c7e947963d3170417c469df 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/sample_2.wav +++ b/examples/SQA/Public-SG-Speech-QA-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:318f83b136dc48cc2094bbf974094dbde6c3872a5f0c0bce99b206644bd9822d -size 1681722 +oid sha256:800921b94cc36ce5f56520c1a5c26dc73f9031eb24de48bc11d16dd8c7f80c00 +size 1582308 diff --git a/examples/SQA/Public-SG-Speech-QA-Test/state.json b/examples/SQA/Public-SG-Speech-QA-Test/state.json index 3a16cade1f2154b599ff0ee007e06680bcb75c72..5a11a8a07f71ff51cae40c876c2e4a5fc531f9fa 100644 --- a/examples/SQA/Public-SG-Speech-QA-Test/state.json +++ b/examples/SQA/Public-SG-Speech-QA-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "caccddb9c34b3f21", + "_fingerprint": "b0302ebb738040ae", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SQA/SLUE-P2-SQA5-Test/data-00000-of-00001.arrow b/examples/SQA/SLUE-P2-SQA5-Test/data-00000-of-00001.arrow index 0302dfcdbbcc17118c9a209ffb3c8018c110b852..fa234b472ca59349d78f644dd1e4987efc7c59f7 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/data-00000-of-00001.arrow +++ b/examples/SQA/SLUE-P2-SQA5-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8f4a692d5fcaee04885bcd8277fda55578e6135813ed8ae2cdf1fade8757109e -size 5222928 +oid sha256:94672a0af2a89f0b79660775679da0f6525d466768be9b1e601b1d4ea8b83dd7 +size 6701344 diff --git a/examples/SQA/SLUE-P2-SQA5-Test/dataset_info.json b/examples/SQA/SLUE-P2-SQA5-Test/dataset_info.json index e1666dfd561139c081bd34bc111a1ef188c97c19..86bd315177f7f0cd34dc82024e129dead305e797 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/dataset_info.json +++ b/examples/SQA/SLUE-P2-SQA5-Test/dataset_info.json @@ -208,6 +208,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SQA/SLUE-P2-SQA5-Test/sample_0.wav b/examples/SQA/SLUE-P2-SQA5-Test/sample_0.wav index 38fa05167e518b91abbbe3892e2ab3488c3fc66d..6e4c05d91ecb84f443abbfbabc82da60978273e7 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/sample_0.wav +++ b/examples/SQA/SLUE-P2-SQA5-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2ea083853548cf7fb7e9659ee3e29f290c22eeef99b5316251f7e80023cbe882 +oid sha256:f424fa8c7b24686552843dc455c47f0809be6acb8305e1b69f948a35d3b241ba size 1280044 diff --git a/examples/SQA/SLUE-P2-SQA5-Test/sample_1.wav b/examples/SQA/SLUE-P2-SQA5-Test/sample_1.wav index ee433bdb91f66bd32b140fb05fd9f6a0d51be495..2f6322867b367896e869e5dae52c1698053f15fd 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/sample_1.wav +++ b/examples/SQA/SLUE-P2-SQA5-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9f67f52bd5eb7a6402b642dc3edc201ef924651fb52dc7fe2d4b2197bbe6bbd6 +oid sha256:68edf517c7e1a3066d2495fe6bfcf7ea3ddedcd4e26a5ff473ede1fa87611fa9 size 1280044 diff --git a/examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav b/examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav index 559d54546827e6e9117535bbc50f915adfa61b5a..4d5d2ad207ca9da3e4289359470a35153cb9586d 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav +++ b/examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:85c1b5d9896f4db27484d593385d62cd3b3887e1d590b87373d2d8fd97f7da05 +oid sha256:b9047589d0e1182f4896ea5f78ce42db5e18a8b8f108e12a30314ef9923cb251 size 1280044 diff --git a/examples/SQA/SLUE-P2-SQA5-Test/state.json b/examples/SQA/SLUE-P2-SQA5-Test/state.json index 9269d6748a4b83722969b0997a02f1a9ebf3807c..59716c7718929b75a9009693e6e03819c405852f 100644 --- a/examples/SQA/SLUE-P2-SQA5-Test/state.json +++ b/examples/SQA/SLUE-P2-SQA5-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "e3c5a96704e595fe", + "_fingerprint": "cfb427c947a66153", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/SQA/Spoken-Squad-Test/data-00000-of-00001.arrow b/examples/SQA/Spoken-Squad-Test/data-00000-of-00001.arrow index e30bb1b71a5945f5dd699df02203b7fb96d2bfb1..a29f43af482feeadd43a53dc31349fd5498a7cbe 100644 --- a/examples/SQA/Spoken-Squad-Test/data-00000-of-00001.arrow +++ b/examples/SQA/Spoken-Squad-Test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:17b3ee4f250469b7e6dd37590ccbb6b452f7f19b04bcaf5b062d2651aa6e7aec -size 7216392 +oid sha256:c033f967b1199ed27296a6ae57d1d5c44f7fd6b9bbd26dfe5ce77cc2d200ec02 +size 5076136 diff --git a/examples/SQA/Spoken-Squad-Test/dataset_info.json b/examples/SQA/Spoken-Squad-Test/dataset_info.json index 59461f89e6a39255aabddc04d03a28a8b503d28f..87ca2ad59ba2e4ad732172e8a5023b15b7a421b2 100644 --- a/examples/SQA/Spoken-Squad-Test/dataset_info.json +++ b/examples/SQA/Spoken-Squad-Test/dataset_info.json @@ -183,6 +183,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/SQA/Spoken-Squad-Test/sample_0.wav b/examples/SQA/Spoken-Squad-Test/sample_0.wav index 91a45dc9ee12ffac6bfb8838dc863b04567ccb07..f77e635d1a8583b2113adad9ce9513fa00fdb511 100644 --- a/examples/SQA/Spoken-Squad-Test/sample_0.wav +++ b/examples/SQA/Spoken-Squad-Test/sample_0.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:deaac19a31e7bef8a82d98e4b4199d7424ebd7af772fc2bb1fd239af8978b818 -size 1389356 +oid sha256:71e45550a025c916670c73ae1afad384ff61dc17fdda12a4c14d5c8de616502f +size 1609772 diff --git a/examples/SQA/Spoken-Squad-Test/sample_1.wav b/examples/SQA/Spoken-Squad-Test/sample_1.wav index 51bb3dfb86abbc4f666bff1a00a0c57afdfdcf19..8385aa8c76428a40c686f20d423960e1d04fa537 100644 --- a/examples/SQA/Spoken-Squad-Test/sample_1.wav +++ b/examples/SQA/Spoken-Squad-Test/sample_1.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:23bed7b72f1631b75672d718af122340d2ed3c38ce86534f772df5c02cb8d91d -size 2665772 +oid sha256:5221d39a578faa78501214237b63b69a26f7ff526139775c624427c3027062b8 +size 1301804 diff --git a/examples/SQA/Spoken-Squad-Test/sample_2.wav b/examples/SQA/Spoken-Squad-Test/sample_2.wav index 1680d55210201e5299940d1b035fde5d75c75e55..cf969bfe4df8f0fc593b91e80af5642005f4a4e3 100644 --- a/examples/SQA/Spoken-Squad-Test/sample_2.wav +++ b/examples/SQA/Spoken-Squad-Test/sample_2.wav @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c244d0b3cb482c34b19c4fc4d4d15bcb8d49d9b0bf210165d498f745859e2357 -size 3141932 +oid sha256:c1b8cb9df078360ab700196a1ccd77cd9c9b5b5c782174cbd57e5baf51a02bc1 +size 2146604 diff --git a/examples/SQA/Spoken-Squad-Test/state.json b/examples/SQA/Spoken-Squad-Test/state.json index 3657f1896e75f83413b7bb4253530da9c1b1c624..37e4592949482275e6ca8e5270c80c7fe84fcfe9 100644 --- a/examples/SQA/Spoken-Squad-Test/state.json +++ b/examples/SQA/Spoken-Squad-Test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "8482b9acafa077ac", + "_fingerprint": "a67e3cba8fca3ea2", "_format_columns": [ "context", "instruction", @@ -16,7 +16,9 @@ "meralion_audiollm_v1_lora", "whisper_large_v3_with_llama_3_8b_instruct", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-EN-ID-test/data-00000-of-00001.arrow b/examples/ST/Covost2-EN-ID-test/data-00000-of-00001.arrow index 5dd8e3e20f2ad085150346711011cd79047ff75f..c943d6a5890eeef0a668cd8e1ff96593b2a5d1fb 100644 --- a/examples/ST/Covost2-EN-ID-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-EN-ID-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a0390e30c7fd6f5c18b37f622f8784052c6b23149f141b4540cb59f6cd7b9c69 -size 523560 +oid sha256:0b49a848656b56a3d15f80effd1887c508e32883b7cb8ae6dc9058a292b80718 +size 614752 diff --git a/examples/ST/Covost2-EN-ID-test/dataset_info.json b/examples/ST/Covost2-EN-ID-test/dataset_info.json index b25db6989f0e56b64fa01d76c2fb75832a886b5e..00f437e3bc4e38d963d0fd4e8d64252fc7d04a9e 100644 --- a/examples/ST/Covost2-EN-ID-test/dataset_info.json +++ b/examples/ST/Covost2-EN-ID-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-EN-ID-test/sample_0.wav b/examples/ST/Covost2-EN-ID-test/sample_0.wav index 25c2b5a12d15e235eb9aed64a3c872d32edba496..79cbee9dbba510dacefbad9bdb1bc3abda23840a 100644 Binary files a/examples/ST/Covost2-EN-ID-test/sample_0.wav and b/examples/ST/Covost2-EN-ID-test/sample_0.wav differ diff --git a/examples/ST/Covost2-EN-ID-test/sample_1.wav b/examples/ST/Covost2-EN-ID-test/sample_1.wav index 2b89ba1a9ffe0b5d8c0659c9410edc725f6b2dd7..326ecdfa6a372b60dba3356a2ec51d390eca4407 100644 Binary files a/examples/ST/Covost2-EN-ID-test/sample_1.wav and b/examples/ST/Covost2-EN-ID-test/sample_1.wav differ diff --git a/examples/ST/Covost2-EN-ID-test/sample_2.wav b/examples/ST/Covost2-EN-ID-test/sample_2.wav index f3431117fb2b3a42a63c3138a0605ca0b0046ca5..51b8b78b7f0506592ececdce3e4859db85a7addd 100644 Binary files a/examples/ST/Covost2-EN-ID-test/sample_2.wav and b/examples/ST/Covost2-EN-ID-test/sample_2.wav differ diff --git a/examples/ST/Covost2-EN-ID-test/state.json b/examples/ST/Covost2-EN-ID-test/state.json index 9b4dc3f7b4960563f749f82c2c02bcc2666ea115..bf265fca65a3870d12173edd9ac84ac5cac89f9b 100644 --- a/examples/ST/Covost2-EN-ID-test/state.json +++ b/examples/ST/Covost2-EN-ID-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "45aac62476189dab", + "_fingerprint": "57213df4e488b515", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-EN-TA-test/data-00000-of-00001.arrow b/examples/ST/Covost2-EN-TA-test/data-00000-of-00001.arrow index 822e8ea669c238d7db916fece41251b84f1a1471..199aac98702f92eef52880dfccf8e2727413f6d0 100644 --- a/examples/ST/Covost2-EN-TA-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-EN-TA-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1dc2cff5380f28f45b6188f0eaf096a15207c693026a5854c04dc8d57887faba -size 576424 +oid sha256:5f8b0c8b2fa09b82c3c74385eb859ec9f65205c1bee57840a320da38b4e269ea +size 618224 diff --git a/examples/ST/Covost2-EN-TA-test/dataset_info.json b/examples/ST/Covost2-EN-TA-test/dataset_info.json index b25db6989f0e56b64fa01d76c2fb75832a886b5e..00f437e3bc4e38d963d0fd4e8d64252fc7d04a9e 100644 --- a/examples/ST/Covost2-EN-TA-test/dataset_info.json +++ b/examples/ST/Covost2-EN-TA-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-EN-TA-test/sample_0.wav b/examples/ST/Covost2-EN-TA-test/sample_0.wav index f5cc0d779f3accaa6dff1dcc3f76c6c9b7370446..67b7cb250b46c0a3a77795fbdd05a806cba6abe2 100644 Binary files a/examples/ST/Covost2-EN-TA-test/sample_0.wav and b/examples/ST/Covost2-EN-TA-test/sample_0.wav differ diff --git a/examples/ST/Covost2-EN-TA-test/sample_1.wav b/examples/ST/Covost2-EN-TA-test/sample_1.wav index 3aff66d4d7e2772192d6b37dc0e0142fc57adb0f..ed4c0ad76c3b4f69ff6d0c84e1260900e58ac77b 100644 Binary files a/examples/ST/Covost2-EN-TA-test/sample_1.wav and b/examples/ST/Covost2-EN-TA-test/sample_1.wav differ diff --git a/examples/ST/Covost2-EN-TA-test/sample_2.wav b/examples/ST/Covost2-EN-TA-test/sample_2.wav index 188a2b20fa8c2612762b09e774ace9f070b8aff0..1ab1bbe097a923ff496659488d4dcec937a2a19e 100644 Binary files a/examples/ST/Covost2-EN-TA-test/sample_2.wav and b/examples/ST/Covost2-EN-TA-test/sample_2.wav differ diff --git a/examples/ST/Covost2-EN-TA-test/state.json b/examples/ST/Covost2-EN-TA-test/state.json index 5e91574d7cd30ff6ea2a8f7fb95ce8d2f0890a83..5ab7973ff8c03a8bfa8ca87ba8b670fc50416588 100644 --- a/examples/ST/Covost2-EN-TA-test/state.json +++ b/examples/ST/Covost2-EN-TA-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "e30a809aaa184c6f", + "_fingerprint": "b1c4138a50cf04d9", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-EN-ZH-test/data-00000-of-00001.arrow b/examples/ST/Covost2-EN-ZH-test/data-00000-of-00001.arrow index b24a1fc60c363fa42e0df37710f1165c1908d10e..1f374dabc9059ccadabbc4f0e63b6de474b1cd43 100644 --- a/examples/ST/Covost2-EN-ZH-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-EN-ZH-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:df30bbb05d12ef63de76b4596fed8637846c580e01e8d1d7a8ebda41bac4d37f -size 398616 +oid sha256:6057c577bf4083aa060c368fd793503fe84fbb995ad82e6af4888b0da9f4ea2c +size 597264 diff --git a/examples/ST/Covost2-EN-ZH-test/dataset_info.json b/examples/ST/Covost2-EN-ZH-test/dataset_info.json index b25db6989f0e56b64fa01d76c2fb75832a886b5e..00f437e3bc4e38d963d0fd4e8d64252fc7d04a9e 100644 --- a/examples/ST/Covost2-EN-ZH-test/dataset_info.json +++ b/examples/ST/Covost2-EN-ZH-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-EN-ZH-test/sample_0.wav b/examples/ST/Covost2-EN-ZH-test/sample_0.wav index ebe2b681a9e476cf91aa9f2a2541a57988454221..9c565285442164234a86ec3e9a894a5bba93afdd 100644 Binary files a/examples/ST/Covost2-EN-ZH-test/sample_0.wav and b/examples/ST/Covost2-EN-ZH-test/sample_0.wav differ diff --git a/examples/ST/Covost2-EN-ZH-test/sample_1.wav b/examples/ST/Covost2-EN-ZH-test/sample_1.wav index dfac27d0e29080bd490e51ed86a09a4804eb5ff1..21cabb1cca979df07f4f9510aa7787527f9f674f 100644 Binary files a/examples/ST/Covost2-EN-ZH-test/sample_1.wav and b/examples/ST/Covost2-EN-ZH-test/sample_1.wav differ diff --git a/examples/ST/Covost2-EN-ZH-test/sample_2.wav b/examples/ST/Covost2-EN-ZH-test/sample_2.wav index 1b3be50610325f271c28947bd1fa44c6586d6fe2..87464ae08e8cc98adb3d8f57ab229b0c41b58a9d 100644 Binary files a/examples/ST/Covost2-EN-ZH-test/sample_2.wav and b/examples/ST/Covost2-EN-ZH-test/sample_2.wav differ diff --git a/examples/ST/Covost2-EN-ZH-test/state.json b/examples/ST/Covost2-EN-ZH-test/state.json index 531e57e55ef2ebf6d0e2336fb125c4db42b0f9c8..9fde124d9547b2815aee087a470c29d89574d45a 100644 --- a/examples/ST/Covost2-EN-ZH-test/state.json +++ b/examples/ST/Covost2-EN-ZH-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "8089a8574e5ffd7a", + "_fingerprint": "c3cc61a4f41eb22d", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-ID-EN-test/data-00000-of-00001.arrow b/examples/ST/Covost2-ID-EN-test/data-00000-of-00001.arrow index 370186e346c6087b6ed4e54ebf63a026cabd6ef2..011fefd694765410f44dae9375a2ec3735589529 100644 --- a/examples/ST/Covost2-ID-EN-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-ID-EN-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d80d8028a29587ce439219ba6729b6fdfee1e29154221045944f295541f1a146 -size 568024 +oid sha256:f8d6b6c216c8c689b1560635df39996f29f9da1b4a61a8dfcab07c358d54f94c +size 286464 diff --git a/examples/ST/Covost2-ID-EN-test/dataset_info.json b/examples/ST/Covost2-ID-EN-test/dataset_info.json index b25db6989f0e56b64fa01d76c2fb75832a886b5e..00f437e3bc4e38d963d0fd4e8d64252fc7d04a9e 100644 --- a/examples/ST/Covost2-ID-EN-test/dataset_info.json +++ b/examples/ST/Covost2-ID-EN-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-ID-EN-test/sample_0.wav b/examples/ST/Covost2-ID-EN-test/sample_0.wav index 953755836980bd4b6cd2968d39e255ed0f199bfe..b97aba339a48366a77b228664d720fc65cc2cba2 100644 Binary files a/examples/ST/Covost2-ID-EN-test/sample_0.wav and b/examples/ST/Covost2-ID-EN-test/sample_0.wav differ diff --git a/examples/ST/Covost2-ID-EN-test/sample_1.wav b/examples/ST/Covost2-ID-EN-test/sample_1.wav index 5302d7d0ff51cdce307b5fbb5ec7c3cc61bd8ee8..07166bc59e703f67979834e6070a3455d63124cb 100644 Binary files a/examples/ST/Covost2-ID-EN-test/sample_1.wav and b/examples/ST/Covost2-ID-EN-test/sample_1.wav differ diff --git a/examples/ST/Covost2-ID-EN-test/sample_2.wav b/examples/ST/Covost2-ID-EN-test/sample_2.wav index d01013320d93fa16a15ee38383b01dce205c6989..242a2b8433daafc73f21ab8757c733c654942d88 100644 Binary files a/examples/ST/Covost2-ID-EN-test/sample_2.wav and b/examples/ST/Covost2-ID-EN-test/sample_2.wav differ diff --git a/examples/ST/Covost2-ID-EN-test/state.json b/examples/ST/Covost2-ID-EN-test/state.json index ccf75843fd30ff7f8653f7a9820c53ddece757b4..74d70d529f7e6556daa4d8aaa323188bef587e2a 100644 --- a/examples/ST/Covost2-ID-EN-test/state.json +++ b/examples/ST/Covost2-ID-EN-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "86eef937bbaf81f4", + "_fingerprint": "14a85b50e56a9375", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-TA-EN-test/data-00000-of-00001.arrow b/examples/ST/Covost2-TA-EN-test/data-00000-of-00001.arrow index 229b5f65f3ff5ac118f64f82c1117a42e18dabf1..af99a4767b1f191c49f1dace9769fd38611fb8b1 100644 --- a/examples/ST/Covost2-TA-EN-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-TA-EN-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8bb4fe085f89698275aa7972d0023750e3efce2c0adef0af7a0b8e1a2351c985 -size 393168 +oid sha256:20f12ef73159b4680e2b3c5f60d75e78c850c6d2eb4d31a0f75767792e9c20b5 +size 398576 diff --git a/examples/ST/Covost2-TA-EN-test/dataset_info.json b/examples/ST/Covost2-TA-EN-test/dataset_info.json index 63cdba3ce5662d2c70078e2343b090c3f42aa100..f31d1a65ddb36b0d3e29fe4a0bb8bf6650b6f7ff 100644 --- a/examples/ST/Covost2-TA-EN-test/dataset_info.json +++ b/examples/ST/Covost2-TA-EN-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-TA-EN-test/sample_0.wav b/examples/ST/Covost2-TA-EN-test/sample_0.wav index a930e9d6ecdf71d1a5c482512d317fc0d774d231..0a3376517a82b09818a184da9c2f3c14aa3f38c1 100644 Binary files a/examples/ST/Covost2-TA-EN-test/sample_0.wav and b/examples/ST/Covost2-TA-EN-test/sample_0.wav differ diff --git a/examples/ST/Covost2-TA-EN-test/sample_1.wav b/examples/ST/Covost2-TA-EN-test/sample_1.wav index 20c17bae309b829001b09cf6376675f9210ff751..46fc48c3f378eaa58855f4dc8e38fb0597ce4762 100644 Binary files a/examples/ST/Covost2-TA-EN-test/sample_1.wav and b/examples/ST/Covost2-TA-EN-test/sample_1.wav differ diff --git a/examples/ST/Covost2-TA-EN-test/sample_2.wav b/examples/ST/Covost2-TA-EN-test/sample_2.wav index eaa8c8c0cfa770f7ebc137f70c07bceea40046d9..a11b6d014f126353e22677890386e744c736e46e 100644 Binary files a/examples/ST/Covost2-TA-EN-test/sample_2.wav and b/examples/ST/Covost2-TA-EN-test/sample_2.wav differ diff --git a/examples/ST/Covost2-TA-EN-test/state.json b/examples/ST/Covost2-TA-EN-test/state.json index 1fa35e273c3e8ee0d8bb7c397deadf9509f8b56f..cfaa5399cf989495b87508fd4bc240ec966d0e70 100644 --- a/examples/ST/Covost2-TA-EN-test/state.json +++ b/examples/ST/Covost2-TA-EN-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "93608e86f8b7524b", + "_fingerprint": "d51efd3faac61ff1", "_format_columns": [ "answer", "context", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null, diff --git a/examples/ST/Covost2-ZH-EN-test/data-00000-of-00001.arrow b/examples/ST/Covost2-ZH-EN-test/data-00000-of-00001.arrow index d17e47b203a0bbde458ca1bccdf5027d205aa831..4374d4655c760a18495d798591dbb78c74a8e6f1 100644 --- a/examples/ST/Covost2-ZH-EN-test/data-00000-of-00001.arrow +++ b/examples/ST/Covost2-ZH-EN-test/data-00000-of-00001.arrow @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ddb93d2266e005d13a6a9ba5f3ea7a6ee0192657c55d435fdde3fc27fac715ef -size 623552 +oid sha256:b93743ebab5f632991576a223edbbb9b30a3facdaa83fbee5f680ece0ea595df +size 595408 diff --git a/examples/ST/Covost2-ZH-EN-test/dataset_info.json b/examples/ST/Covost2-ZH-EN-test/dataset_info.json index b25db6989f0e56b64fa01d76c2fb75832a886b5e..00f437e3bc4e38d963d0fd4e8d64252fc7d04a9e 100644 --- a/examples/ST/Covost2-ZH-EN-test/dataset_info.json +++ b/examples/ST/Covost2-ZH-EN-test/dataset_info.json @@ -165,6 +165,42 @@ "dtype": "string", "_type": "Value" } + }, + "meralion_audiollm_v1_mse": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } + }, + "stage2_whisper3_fft_mlp100_gemma2_9b_lora": { + "answer": { + "dtype": "string", + "_type": "Value" + }, + "model_prediction": { + "dtype": "string", + "_type": "Value" + }, + "task_type": { + "dtype": "string", + "_type": "Value" + }, + "text": { + "dtype": "string", + "_type": "Value" + } } }, "homepage": "", diff --git a/examples/ST/Covost2-ZH-EN-test/sample_0.wav b/examples/ST/Covost2-ZH-EN-test/sample_0.wav index b287e87b0a79fc0c8b8c25cbbe54a201e0201592..51fda98fa7902d9136ffd7b16bc35d4f87bc69c0 100644 Binary files a/examples/ST/Covost2-ZH-EN-test/sample_0.wav and b/examples/ST/Covost2-ZH-EN-test/sample_0.wav differ diff --git a/examples/ST/Covost2-ZH-EN-test/sample_1.wav b/examples/ST/Covost2-ZH-EN-test/sample_1.wav index 25cec91737fb23243bb76c92b6077da6d3acc357..77a752cd09878367b509cf5b7ff7a02e0cd6584c 100644 Binary files a/examples/ST/Covost2-ZH-EN-test/sample_1.wav and b/examples/ST/Covost2-ZH-EN-test/sample_1.wav differ diff --git a/examples/ST/Covost2-ZH-EN-test/sample_2.wav b/examples/ST/Covost2-ZH-EN-test/sample_2.wav index 78b1a729ea55854f60d3d1c91b40704ed23bd42e..e3c5dfdefaeef44d1485473840f29e1d9a8d436c 100644 Binary files a/examples/ST/Covost2-ZH-EN-test/sample_2.wav and b/examples/ST/Covost2-ZH-EN-test/sample_2.wav differ diff --git a/examples/ST/Covost2-ZH-EN-test/state.json b/examples/ST/Covost2-ZH-EN-test/state.json index 3c449d398d13af1bb2ffddab3dd7f8a8fd373a41..f474d58d7310038184abab8ae57d299d438cf3d9 100644 --- a/examples/ST/Covost2-ZH-EN-test/state.json +++ b/examples/ST/Covost2-ZH-EN-test/state.json @@ -4,7 +4,7 @@ "filename": "data-00000-of-00001.arrow" } ], - "_fingerprint": "98d00264fe4b6901", + "_fingerprint": "625b19333ed981d2", "_format_columns": [ "context", "instruction", @@ -15,7 +15,9 @@ "Qwen2-Audio-7B-Instruct", "meralion_audiollm_v1_lora", "mowe_audio", - "qwen_audio_chat" + "qwen_audio_chat", + "meralion_audiollm_v1_mse", + "stage2_whisper3_fft_mlp100_gemma2_9b_lora" ], "_format_kwargs": {}, "_format_type": null,