Spaces:
Running
Running
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +18 -0
- examples/AC/AudioCaps-Test/data-00000-of-00001.arrow +3 -0
- examples/AC/AudioCaps-Test/dataset_info.json +142 -0
- examples/AC/AudioCaps-Test/sample_0.wav +0 -0
- examples/AC/AudioCaps-Test/sample_1.wav +0 -0
- examples/AC/AudioCaps-Test/sample_2.wav +0 -0
- examples/AC/AudioCaps-Test/state.json +23 -0
- examples/AC/WavCaps-Test/data-00000-of-00001.arrow +3 -0
- examples/AC/WavCaps-Test/dataset_info.json +138 -0
- examples/AC/WavCaps-Test/sample_0.wav +0 -0
- examples/AC/WavCaps-Test/sample_1.wav +0 -0
- examples/AC/WavCaps-Test/sample_2.wav +0 -0
- examples/AC/WavCaps-Test/state.json +23 -0
- examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow +3 -0
- examples/AR/VoxCeleb-Accent-Test/dataset_info.json +150 -0
- examples/AR/VoxCeleb-Accent-Test/sample_0.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/sample_1.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/sample_2.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/state.json +23 -0
- examples/ASQA/AudioCaps-QA-Test/data-00000-of-00001.arrow +3 -0
- examples/ASQA/AudioCaps-QA-Test/dataset_info.json +146 -0
- examples/ASQA/AudioCaps-QA-Test/sample_0.wav +0 -0
- examples/ASQA/AudioCaps-QA-Test/sample_1.wav +0 -0
- examples/ASQA/AudioCaps-QA-Test/sample_2.wav +0 -0
- examples/ASQA/AudioCaps-QA-Test/state.json +23 -0
- examples/ASQA/Clotho-AQA-Test/data-00000-of-00001.arrow +3 -0
- examples/ASQA/Clotho-AQA-Test/dataset_info.json +129 -0
- examples/ASQA/Clotho-AQA-Test/sample_0.wav +0 -0
- examples/ASQA/Clotho-AQA-Test/sample_1.wav +0 -0
- examples/ASQA/Clotho-AQA-Test/sample_2.wav +0 -0
- examples/ASQA/Clotho-AQA-Test/state.json +23 -0
- examples/ASQA/WavCaps-QA-Test/data-00000-of-00001.arrow +3 -0
- examples/ASQA/WavCaps-QA-Test/dataset_info.json +142 -0
- examples/ASQA/WavCaps-QA-Test/sample_0.wav +0 -0
- examples/ASQA/WavCaps-QA-Test/sample_1.wav +0 -0
- examples/ASQA/WavCaps-QA-Test/sample_2.wav +0 -0
- examples/ASQA/WavCaps-QA-Test/state.json +23 -0
- examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow +3 -0
- examples/ASR/Common-Voice-15-En-Test/dataset_info.json +170 -0
- examples/ASR/Common-Voice-15-En-Test/sample_0.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/sample_1.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/sample_2.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/state.json +23 -0
- examples/ASR/Earnings21-Test/data-00000-of-00001.arrow +3 -0
- examples/ASR/Earnings21-Test/dataset_info.json +134 -0
- examples/ASR/Earnings21-Test/sample_0.wav +3 -0
- examples/ASR/Earnings21-Test/sample_1.wav +3 -0
- examples/ASR/Earnings21-Test/sample_2.wav +3 -0
- examples/ASR/Earnings21-Test/state.json +23 -0
- examples/ASR/Earnings22-Test/data-00000-of-00001.arrow +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,21 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
scale-hf-logo.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
scale-hf-logo.png filter=lfs diff=lfs merge=lfs -text
|
36 |
+
examples/ASR/Earnings21-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
37 |
+
examples/ASR/Earnings21-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
38 |
+
examples/ASR/Earnings21-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
39 |
+
examples/ASR/Earnings22-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
40 |
+
examples/ASR/Earnings22-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
41 |
+
examples/ASR/Earnings22-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
42 |
+
examples/ASR/Tedlium3-Longform-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
43 |
+
examples/ASR/Tedlium3-Longform-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
44 |
+
examples/ASR/Tedlium3-Longform-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
45 |
+
examples/SQA/DREAM-TTS-MCQ-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
46 |
+
examples/SQA/Public-SG-Speech-QA-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
47 |
+
examples/SQA/Public-SG-Speech-QA-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
48 |
+
examples/SQA/SLUE-P2-SQA5-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
49 |
+
examples/SQA/SLUE-P2-SQA5-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
50 |
+
examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
51 |
+
examples/SQA/Spoken-Squad-v1/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
52 |
+
examples/SQA/Spoken-Squad-v1/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
53 |
+
examples/SQA/Spoken-Squad-v1/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
examples/AC/AudioCaps-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff53d7bcff873fea97f02e971836f24adfbfba9ebdcfc7554423bf65cb110e1d
|
3 |
+
size 970312
|
examples/AC/AudioCaps-Test/dataset_info.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"audiocap_id": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"start_time": {
|
41 |
+
"dtype": "string",
|
42 |
+
"_type": "Value"
|
43 |
+
},
|
44 |
+
"youtube_id": {
|
45 |
+
"dtype": "string",
|
46 |
+
"_type": "Value"
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"salmonn_7b": {
|
50 |
+
"answer": {
|
51 |
+
"dtype": "string",
|
52 |
+
"_type": "Value"
|
53 |
+
},
|
54 |
+
"model_prediction": {
|
55 |
+
"dtype": "string",
|
56 |
+
"_type": "Value"
|
57 |
+
},
|
58 |
+
"task_type": {
|
59 |
+
"dtype": "string",
|
60 |
+
"_type": "Value"
|
61 |
+
},
|
62 |
+
"text": {
|
63 |
+
"dtype": "string",
|
64 |
+
"_type": "Value"
|
65 |
+
}
|
66 |
+
},
|
67 |
+
"wavllm_fairseq": {
|
68 |
+
"answer": {
|
69 |
+
"dtype": "string",
|
70 |
+
"_type": "Value"
|
71 |
+
},
|
72 |
+
"model_prediction": {
|
73 |
+
"dtype": "string",
|
74 |
+
"_type": "Value"
|
75 |
+
},
|
76 |
+
"task_type": {
|
77 |
+
"dtype": "string",
|
78 |
+
"_type": "Value"
|
79 |
+
},
|
80 |
+
"text": {
|
81 |
+
"dtype": "string",
|
82 |
+
"_type": "Value"
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"Qwen2-Audio-7B-Instruct": {
|
86 |
+
"answer": {
|
87 |
+
"dtype": "string",
|
88 |
+
"_type": "Value"
|
89 |
+
},
|
90 |
+
"model_prediction": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
},
|
94 |
+
"task_type": {
|
95 |
+
"dtype": "string",
|
96 |
+
"_type": "Value"
|
97 |
+
},
|
98 |
+
"text": {
|
99 |
+
"dtype": "string",
|
100 |
+
"_type": "Value"
|
101 |
+
}
|
102 |
+
},
|
103 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
104 |
+
"answer": {
|
105 |
+
"dtype": "string",
|
106 |
+
"_type": "Value"
|
107 |
+
},
|
108 |
+
"model_prediction": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
},
|
112 |
+
"task_type": {
|
113 |
+
"dtype": "string",
|
114 |
+
"_type": "Value"
|
115 |
+
},
|
116 |
+
"text": {
|
117 |
+
"dtype": "string",
|
118 |
+
"_type": "Value"
|
119 |
+
}
|
120 |
+
},
|
121 |
+
"qwen_audio_chat": {
|
122 |
+
"answer": {
|
123 |
+
"dtype": "string",
|
124 |
+
"_type": "Value"
|
125 |
+
},
|
126 |
+
"model_prediction": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
},
|
130 |
+
"task_type": {
|
131 |
+
"dtype": "string",
|
132 |
+
"_type": "Value"
|
133 |
+
},
|
134 |
+
"text": {
|
135 |
+
"dtype": "string",
|
136 |
+
"_type": "Value"
|
137 |
+
}
|
138 |
+
}
|
139 |
+
},
|
140 |
+
"homepage": "",
|
141 |
+
"license": ""
|
142 |
+
}
|
examples/AC/AudioCaps-Test/sample_0.wav
ADDED
Binary file (320 kB). View file
|
|
examples/AC/AudioCaps-Test/sample_1.wav
ADDED
Binary file (320 kB). View file
|
|
examples/AC/AudioCaps-Test/sample_2.wav
ADDED
Binary file (320 kB). View file
|
|
examples/AC/AudioCaps-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "0e301916c3676d35",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/AC/WavCaps-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c824145183da91da498c0338860b6daeaed94d7c619ec9ae22a041918c61c902
|
3 |
+
size 985360
|
examples/AC/WavCaps-Test/dataset_info.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"audio_path": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"duration": {
|
41 |
+
"dtype": "string",
|
42 |
+
"_type": "Value"
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"salmonn_7b": {
|
46 |
+
"answer": {
|
47 |
+
"dtype": "string",
|
48 |
+
"_type": "Value"
|
49 |
+
},
|
50 |
+
"model_prediction": {
|
51 |
+
"dtype": "string",
|
52 |
+
"_type": "Value"
|
53 |
+
},
|
54 |
+
"task_type": {
|
55 |
+
"dtype": "string",
|
56 |
+
"_type": "Value"
|
57 |
+
},
|
58 |
+
"text": {
|
59 |
+
"dtype": "string",
|
60 |
+
"_type": "Value"
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"wavllm_fairseq": {
|
64 |
+
"answer": {
|
65 |
+
"dtype": "string",
|
66 |
+
"_type": "Value"
|
67 |
+
},
|
68 |
+
"model_prediction": {
|
69 |
+
"dtype": "string",
|
70 |
+
"_type": "Value"
|
71 |
+
},
|
72 |
+
"task_type": {
|
73 |
+
"dtype": "string",
|
74 |
+
"_type": "Value"
|
75 |
+
},
|
76 |
+
"text": {
|
77 |
+
"dtype": "string",
|
78 |
+
"_type": "Value"
|
79 |
+
}
|
80 |
+
},
|
81 |
+
"Qwen2-Audio-7B-Instruct": {
|
82 |
+
"answer": {
|
83 |
+
"dtype": "string",
|
84 |
+
"_type": "Value"
|
85 |
+
},
|
86 |
+
"model_prediction": {
|
87 |
+
"dtype": "string",
|
88 |
+
"_type": "Value"
|
89 |
+
},
|
90 |
+
"task_type": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
},
|
94 |
+
"text": {
|
95 |
+
"dtype": "string",
|
96 |
+
"_type": "Value"
|
97 |
+
}
|
98 |
+
},
|
99 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
100 |
+
"answer": {
|
101 |
+
"dtype": "string",
|
102 |
+
"_type": "Value"
|
103 |
+
},
|
104 |
+
"model_prediction": {
|
105 |
+
"dtype": "string",
|
106 |
+
"_type": "Value"
|
107 |
+
},
|
108 |
+
"task_type": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
},
|
112 |
+
"text": {
|
113 |
+
"dtype": "string",
|
114 |
+
"_type": "Value"
|
115 |
+
}
|
116 |
+
},
|
117 |
+
"qwen_audio_chat": {
|
118 |
+
"answer": {
|
119 |
+
"dtype": "string",
|
120 |
+
"_type": "Value"
|
121 |
+
},
|
122 |
+
"model_prediction": {
|
123 |
+
"dtype": "string",
|
124 |
+
"_type": "Value"
|
125 |
+
},
|
126 |
+
"task_type": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
},
|
130 |
+
"text": {
|
131 |
+
"dtype": "string",
|
132 |
+
"_type": "Value"
|
133 |
+
}
|
134 |
+
}
|
135 |
+
},
|
136 |
+
"homepage": "",
|
137 |
+
"license": ""
|
138 |
+
}
|
examples/AC/WavCaps-Test/sample_0.wav
ADDED
Binary file (559 kB). View file
|
|
examples/AC/WavCaps-Test/sample_1.wav
ADDED
Binary file (129 kB). View file
|
|
examples/AC/WavCaps-Test/sample_2.wav
ADDED
Binary file (287 kB). View file
|
|
examples/AC/WavCaps-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "1e570096603c2a32",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1c07c0e241fb703dda0b7544925d0ca59bba57417daa5e08727a9edd9312e64
|
3 |
+
size 578840
|
examples/AR/VoxCeleb-Accent-Test/dataset_info.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"Gender": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"Nationality": {
|
41 |
+
"dtype": "string",
|
42 |
+
"_type": "Value"
|
43 |
+
},
|
44 |
+
"VGGFace1 ID": {
|
45 |
+
"dtype": "string",
|
46 |
+
"_type": "Value"
|
47 |
+
},
|
48 |
+
"VoxCeleb1 ID": {
|
49 |
+
"dtype": "string",
|
50 |
+
"_type": "Value"
|
51 |
+
},
|
52 |
+
"index": {
|
53 |
+
"dtype": "string",
|
54 |
+
"_type": "Value"
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"salmonn_7b": {
|
58 |
+
"answer": {
|
59 |
+
"dtype": "string",
|
60 |
+
"_type": "Value"
|
61 |
+
},
|
62 |
+
"model_prediction": {
|
63 |
+
"dtype": "string",
|
64 |
+
"_type": "Value"
|
65 |
+
},
|
66 |
+
"task_type": {
|
67 |
+
"dtype": "string",
|
68 |
+
"_type": "Value"
|
69 |
+
},
|
70 |
+
"text": {
|
71 |
+
"dtype": "string",
|
72 |
+
"_type": "Value"
|
73 |
+
}
|
74 |
+
},
|
75 |
+
"wavllm_fairseq": {
|
76 |
+
"answer": {
|
77 |
+
"dtype": "string",
|
78 |
+
"_type": "Value"
|
79 |
+
},
|
80 |
+
"model_prediction": {
|
81 |
+
"dtype": "string",
|
82 |
+
"_type": "Value"
|
83 |
+
},
|
84 |
+
"task_type": {
|
85 |
+
"dtype": "string",
|
86 |
+
"_type": "Value"
|
87 |
+
},
|
88 |
+
"text": {
|
89 |
+
"dtype": "string",
|
90 |
+
"_type": "Value"
|
91 |
+
}
|
92 |
+
},
|
93 |
+
"Qwen2-Audio-7B-Instruct": {
|
94 |
+
"answer": {
|
95 |
+
"dtype": "string",
|
96 |
+
"_type": "Value"
|
97 |
+
},
|
98 |
+
"model_prediction": {
|
99 |
+
"dtype": "string",
|
100 |
+
"_type": "Value"
|
101 |
+
},
|
102 |
+
"task_type": {
|
103 |
+
"dtype": "string",
|
104 |
+
"_type": "Value"
|
105 |
+
},
|
106 |
+
"text": {
|
107 |
+
"dtype": "string",
|
108 |
+
"_type": "Value"
|
109 |
+
}
|
110 |
+
},
|
111 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
112 |
+
"answer": {
|
113 |
+
"dtype": "string",
|
114 |
+
"_type": "Value"
|
115 |
+
},
|
116 |
+
"model_prediction": {
|
117 |
+
"dtype": "string",
|
118 |
+
"_type": "Value"
|
119 |
+
},
|
120 |
+
"task_type": {
|
121 |
+
"dtype": "string",
|
122 |
+
"_type": "Value"
|
123 |
+
},
|
124 |
+
"text": {
|
125 |
+
"dtype": "string",
|
126 |
+
"_type": "Value"
|
127 |
+
}
|
128 |
+
},
|
129 |
+
"qwen_audio_chat": {
|
130 |
+
"answer": {
|
131 |
+
"dtype": "string",
|
132 |
+
"_type": "Value"
|
133 |
+
},
|
134 |
+
"model_prediction": {
|
135 |
+
"dtype": "string",
|
136 |
+
"_type": "Value"
|
137 |
+
},
|
138 |
+
"task_type": {
|
139 |
+
"dtype": "string",
|
140 |
+
"_type": "Value"
|
141 |
+
},
|
142 |
+
"text": {
|
143 |
+
"dtype": "string",
|
144 |
+
"_type": "Value"
|
145 |
+
}
|
146 |
+
}
|
147 |
+
},
|
148 |
+
"homepage": "",
|
149 |
+
"license": ""
|
150 |
+
}
|
examples/AR/VoxCeleb-Accent-Test/sample_0.wav
ADDED
Binary file (209 kB). View file
|
|
examples/AR/VoxCeleb-Accent-Test/sample_1.wav
ADDED
Binary file (227 kB). View file
|
|
examples/AR/VoxCeleb-Accent-Test/sample_2.wav
ADDED
Binary file (134 kB). View file
|
|
examples/AR/VoxCeleb-Accent-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "7017504c8eeb5d71",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASQA/AudioCaps-QA-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42f33a60a23ffc8fce090307d530ef03b2b8cf9852fa70418e76ed6a1d5dd978
|
3 |
+
size 954480
|
examples/ASQA/AudioCaps-QA-Test/dataset_info.json
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"audiocap_id": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"caption": {
|
41 |
+
"dtype": "string",
|
42 |
+
"_type": "Value"
|
43 |
+
},
|
44 |
+
"start_time": {
|
45 |
+
"dtype": "string",
|
46 |
+
"_type": "Value"
|
47 |
+
},
|
48 |
+
"youtube_id": {
|
49 |
+
"dtype": "string",
|
50 |
+
"_type": "Value"
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"salmonn_7b": {
|
54 |
+
"answer": {
|
55 |
+
"dtype": "string",
|
56 |
+
"_type": "Value"
|
57 |
+
},
|
58 |
+
"model_prediction": {
|
59 |
+
"dtype": "string",
|
60 |
+
"_type": "Value"
|
61 |
+
},
|
62 |
+
"task_type": {
|
63 |
+
"dtype": "string",
|
64 |
+
"_type": "Value"
|
65 |
+
},
|
66 |
+
"text": {
|
67 |
+
"dtype": "string",
|
68 |
+
"_type": "Value"
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"wavllm_fairseq": {
|
72 |
+
"answer": {
|
73 |
+
"dtype": "string",
|
74 |
+
"_type": "Value"
|
75 |
+
},
|
76 |
+
"model_prediction": {
|
77 |
+
"dtype": "string",
|
78 |
+
"_type": "Value"
|
79 |
+
},
|
80 |
+
"task_type": {
|
81 |
+
"dtype": "string",
|
82 |
+
"_type": "Value"
|
83 |
+
},
|
84 |
+
"text": {
|
85 |
+
"dtype": "string",
|
86 |
+
"_type": "Value"
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"Qwen2-Audio-7B-Instruct": {
|
90 |
+
"answer": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
},
|
94 |
+
"model_prediction": {
|
95 |
+
"dtype": "string",
|
96 |
+
"_type": "Value"
|
97 |
+
},
|
98 |
+
"task_type": {
|
99 |
+
"dtype": "string",
|
100 |
+
"_type": "Value"
|
101 |
+
},
|
102 |
+
"text": {
|
103 |
+
"dtype": "string",
|
104 |
+
"_type": "Value"
|
105 |
+
}
|
106 |
+
},
|
107 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
108 |
+
"answer": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
},
|
112 |
+
"model_prediction": {
|
113 |
+
"dtype": "string",
|
114 |
+
"_type": "Value"
|
115 |
+
},
|
116 |
+
"task_type": {
|
117 |
+
"dtype": "string",
|
118 |
+
"_type": "Value"
|
119 |
+
},
|
120 |
+
"text": {
|
121 |
+
"dtype": "string",
|
122 |
+
"_type": "Value"
|
123 |
+
}
|
124 |
+
},
|
125 |
+
"qwen_audio_chat": {
|
126 |
+
"answer": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
},
|
130 |
+
"model_prediction": {
|
131 |
+
"dtype": "string",
|
132 |
+
"_type": "Value"
|
133 |
+
},
|
134 |
+
"task_type": {
|
135 |
+
"dtype": "string",
|
136 |
+
"_type": "Value"
|
137 |
+
},
|
138 |
+
"text": {
|
139 |
+
"dtype": "string",
|
140 |
+
"_type": "Value"
|
141 |
+
}
|
142 |
+
}
|
143 |
+
},
|
144 |
+
"homepage": "",
|
145 |
+
"license": ""
|
146 |
+
}
|
examples/ASQA/AudioCaps-QA-Test/sample_0.wav
ADDED
Binary file (320 kB). View file
|
|
examples/ASQA/AudioCaps-QA-Test/sample_1.wav
ADDED
Binary file (304 kB). View file
|
|
examples/ASQA/AudioCaps-QA-Test/sample_2.wav
ADDED
Binary file (320 kB). View file
|
|
examples/ASQA/AudioCaps-QA-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "b4d0bc420173574a",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASQA/Clotho-AQA-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a76c13e88e89bb39d6a4dedc9f3bb30e128cdaaa5f68d8c0e1d804d9af5cbf68
|
3 |
+
size 2181384
|
examples/ASQA/Clotho-AQA-Test/dataset_info.json
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {},
|
36 |
+
"salmonn_7b": {
|
37 |
+
"answer": {
|
38 |
+
"dtype": "string",
|
39 |
+
"_type": "Value"
|
40 |
+
},
|
41 |
+
"model_prediction": {
|
42 |
+
"dtype": "string",
|
43 |
+
"_type": "Value"
|
44 |
+
},
|
45 |
+
"task_type": {
|
46 |
+
"dtype": "string",
|
47 |
+
"_type": "Value"
|
48 |
+
},
|
49 |
+
"text": {
|
50 |
+
"dtype": "string",
|
51 |
+
"_type": "Value"
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"wavllm_fairseq": {
|
55 |
+
"answer": {
|
56 |
+
"dtype": "string",
|
57 |
+
"_type": "Value"
|
58 |
+
},
|
59 |
+
"model_prediction": {
|
60 |
+
"dtype": "string",
|
61 |
+
"_type": "Value"
|
62 |
+
},
|
63 |
+
"task_type": {
|
64 |
+
"dtype": "string",
|
65 |
+
"_type": "Value"
|
66 |
+
},
|
67 |
+
"text": {
|
68 |
+
"dtype": "string",
|
69 |
+
"_type": "Value"
|
70 |
+
}
|
71 |
+
},
|
72 |
+
"Qwen2-Audio-7B-Instruct": {
|
73 |
+
"answer": {
|
74 |
+
"dtype": "string",
|
75 |
+
"_type": "Value"
|
76 |
+
},
|
77 |
+
"model_prediction": {
|
78 |
+
"dtype": "string",
|
79 |
+
"_type": "Value"
|
80 |
+
},
|
81 |
+
"task_type": {
|
82 |
+
"dtype": "string",
|
83 |
+
"_type": "Value"
|
84 |
+
},
|
85 |
+
"text": {
|
86 |
+
"dtype": "string",
|
87 |
+
"_type": "Value"
|
88 |
+
}
|
89 |
+
},
|
90 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
91 |
+
"answer": {
|
92 |
+
"dtype": "string",
|
93 |
+
"_type": "Value"
|
94 |
+
},
|
95 |
+
"model_prediction": {
|
96 |
+
"dtype": "string",
|
97 |
+
"_type": "Value"
|
98 |
+
},
|
99 |
+
"task_type": {
|
100 |
+
"dtype": "string",
|
101 |
+
"_type": "Value"
|
102 |
+
},
|
103 |
+
"text": {
|
104 |
+
"dtype": "string",
|
105 |
+
"_type": "Value"
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"qwen_audio_chat": {
|
109 |
+
"answer": {
|
110 |
+
"dtype": "string",
|
111 |
+
"_type": "Value"
|
112 |
+
},
|
113 |
+
"model_prediction": {
|
114 |
+
"dtype": "string",
|
115 |
+
"_type": "Value"
|
116 |
+
},
|
117 |
+
"task_type": {
|
118 |
+
"dtype": "string",
|
119 |
+
"_type": "Value"
|
120 |
+
},
|
121 |
+
"text": {
|
122 |
+
"dtype": "string",
|
123 |
+
"_type": "Value"
|
124 |
+
}
|
125 |
+
}
|
126 |
+
},
|
127 |
+
"homepage": "",
|
128 |
+
"license": ""
|
129 |
+
}
|
examples/ASQA/Clotho-AQA-Test/sample_0.wav
ADDED
Binary file (868 kB). View file
|
|
examples/ASQA/Clotho-AQA-Test/sample_1.wav
ADDED
Binary file (668 kB). View file
|
|
examples/ASQA/Clotho-AQA-Test/sample_2.wav
ADDED
Binary file (636 kB). View file
|
|
examples/ASQA/Clotho-AQA-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "3f05c76553bf311d",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASQA/WavCaps-QA-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183517b37463c54c088f5e1011721003d14587380bc111e8ad7f7cfc60fcd9e5
|
3 |
+
size 970376
|
examples/ASQA/WavCaps-QA-Test/dataset_info.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"audio_path": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"caption": {
|
41 |
+
"dtype": "string",
|
42 |
+
"_type": "Value"
|
43 |
+
},
|
44 |
+
"duration": {
|
45 |
+
"dtype": "string",
|
46 |
+
"_type": "Value"
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"salmonn_7b": {
|
50 |
+
"answer": {
|
51 |
+
"dtype": "string",
|
52 |
+
"_type": "Value"
|
53 |
+
},
|
54 |
+
"model_prediction": {
|
55 |
+
"dtype": "string",
|
56 |
+
"_type": "Value"
|
57 |
+
},
|
58 |
+
"task_type": {
|
59 |
+
"dtype": "string",
|
60 |
+
"_type": "Value"
|
61 |
+
},
|
62 |
+
"text": {
|
63 |
+
"dtype": "string",
|
64 |
+
"_type": "Value"
|
65 |
+
}
|
66 |
+
},
|
67 |
+
"wavllm_fairseq": {
|
68 |
+
"answer": {
|
69 |
+
"dtype": "string",
|
70 |
+
"_type": "Value"
|
71 |
+
},
|
72 |
+
"model_prediction": {
|
73 |
+
"dtype": "string",
|
74 |
+
"_type": "Value"
|
75 |
+
},
|
76 |
+
"task_type": {
|
77 |
+
"dtype": "string",
|
78 |
+
"_type": "Value"
|
79 |
+
},
|
80 |
+
"text": {
|
81 |
+
"dtype": "string",
|
82 |
+
"_type": "Value"
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"Qwen2-Audio-7B-Instruct": {
|
86 |
+
"answer": {
|
87 |
+
"dtype": "string",
|
88 |
+
"_type": "Value"
|
89 |
+
},
|
90 |
+
"model_prediction": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
},
|
94 |
+
"task_type": {
|
95 |
+
"dtype": "string",
|
96 |
+
"_type": "Value"
|
97 |
+
},
|
98 |
+
"text": {
|
99 |
+
"dtype": "string",
|
100 |
+
"_type": "Value"
|
101 |
+
}
|
102 |
+
},
|
103 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
104 |
+
"answer": {
|
105 |
+
"dtype": "string",
|
106 |
+
"_type": "Value"
|
107 |
+
},
|
108 |
+
"model_prediction": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
},
|
112 |
+
"task_type": {
|
113 |
+
"dtype": "string",
|
114 |
+
"_type": "Value"
|
115 |
+
},
|
116 |
+
"text": {
|
117 |
+
"dtype": "string",
|
118 |
+
"_type": "Value"
|
119 |
+
}
|
120 |
+
},
|
121 |
+
"qwen_audio_chat": {
|
122 |
+
"answer": {
|
123 |
+
"dtype": "string",
|
124 |
+
"_type": "Value"
|
125 |
+
},
|
126 |
+
"model_prediction": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
},
|
130 |
+
"task_type": {
|
131 |
+
"dtype": "string",
|
132 |
+
"_type": "Value"
|
133 |
+
},
|
134 |
+
"text": {
|
135 |
+
"dtype": "string",
|
136 |
+
"_type": "Value"
|
137 |
+
}
|
138 |
+
}
|
139 |
+
},
|
140 |
+
"homepage": "",
|
141 |
+
"license": ""
|
142 |
+
}
|
examples/ASQA/WavCaps-QA-Test/sample_0.wav
ADDED
Binary file (320 kB). View file
|
|
examples/ASQA/WavCaps-QA-Test/sample_1.wav
ADDED
Binary file (320 kB). View file
|
|
examples/ASQA/WavCaps-QA-Test/sample_2.wav
ADDED
Binary file (320 kB). View file
|
|
examples/ASQA/WavCaps-QA-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "f88396310248e252",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44587f333a31075993f3cc8832f8946fd59605246769dd8bf86887dcf3bd889c
|
3 |
+
size 543912
|
examples/ASR/Common-Voice-15-En-Test/dataset_info.json
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"accents": {
|
37 |
+
"dtype": "null",
|
38 |
+
"_type": "Value"
|
39 |
+
},
|
40 |
+
"age": {
|
41 |
+
"dtype": "null",
|
42 |
+
"_type": "Value"
|
43 |
+
},
|
44 |
+
"client_id": {
|
45 |
+
"dtype": "string",
|
46 |
+
"_type": "Value"
|
47 |
+
},
|
48 |
+
"down_votes": {
|
49 |
+
"dtype": "int64",
|
50 |
+
"_type": "Value"
|
51 |
+
},
|
52 |
+
"gender": {
|
53 |
+
"dtype": "null",
|
54 |
+
"_type": "Value"
|
55 |
+
},
|
56 |
+
"language": {
|
57 |
+
"dtype": "string",
|
58 |
+
"_type": "Value"
|
59 |
+
},
|
60 |
+
"locale": {
|
61 |
+
"dtype": "string",
|
62 |
+
"_type": "Value"
|
63 |
+
},
|
64 |
+
"segment": {
|
65 |
+
"dtype": "null",
|
66 |
+
"_type": "Value"
|
67 |
+
},
|
68 |
+
"up_votes": {
|
69 |
+
"dtype": "int64",
|
70 |
+
"_type": "Value"
|
71 |
+
},
|
72 |
+
"variant": {
|
73 |
+
"dtype": "null",
|
74 |
+
"_type": "Value"
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"salmonn_7b": {
|
78 |
+
"answer": {
|
79 |
+
"dtype": "string",
|
80 |
+
"_type": "Value"
|
81 |
+
},
|
82 |
+
"model_prediction": {
|
83 |
+
"dtype": "string",
|
84 |
+
"_type": "Value"
|
85 |
+
},
|
86 |
+
"task_type": {
|
87 |
+
"dtype": "string",
|
88 |
+
"_type": "Value"
|
89 |
+
},
|
90 |
+
"text": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"wavllm_fairseq": {
|
96 |
+
"answer": {
|
97 |
+
"dtype": "string",
|
98 |
+
"_type": "Value"
|
99 |
+
},
|
100 |
+
"model_prediction": {
|
101 |
+
"dtype": "string",
|
102 |
+
"_type": "Value"
|
103 |
+
},
|
104 |
+
"task_type": {
|
105 |
+
"dtype": "string",
|
106 |
+
"_type": "Value"
|
107 |
+
},
|
108 |
+
"text": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
}
|
112 |
+
},
|
113 |
+
"Qwen2-Audio-7B-Instruct": {
|
114 |
+
"answer": {
|
115 |
+
"dtype": "string",
|
116 |
+
"_type": "Value"
|
117 |
+
},
|
118 |
+
"model_prediction": {
|
119 |
+
"dtype": "string",
|
120 |
+
"_type": "Value"
|
121 |
+
},
|
122 |
+
"task_type": {
|
123 |
+
"dtype": "string",
|
124 |
+
"_type": "Value"
|
125 |
+
},
|
126 |
+
"text": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
}
|
130 |
+
},
|
131 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
132 |
+
"answer": {
|
133 |
+
"dtype": "string",
|
134 |
+
"_type": "Value"
|
135 |
+
},
|
136 |
+
"model_prediction": {
|
137 |
+
"dtype": "string",
|
138 |
+
"_type": "Value"
|
139 |
+
},
|
140 |
+
"task_type": {
|
141 |
+
"dtype": "string",
|
142 |
+
"_type": "Value"
|
143 |
+
},
|
144 |
+
"text": {
|
145 |
+
"dtype": "string",
|
146 |
+
"_type": "Value"
|
147 |
+
}
|
148 |
+
},
|
149 |
+
"qwen_audio_chat": {
|
150 |
+
"answer": {
|
151 |
+
"dtype": "string",
|
152 |
+
"_type": "Value"
|
153 |
+
},
|
154 |
+
"model_prediction": {
|
155 |
+
"dtype": "string",
|
156 |
+
"_type": "Value"
|
157 |
+
},
|
158 |
+
"task_type": {
|
159 |
+
"dtype": "string",
|
160 |
+
"_type": "Value"
|
161 |
+
},
|
162 |
+
"text": {
|
163 |
+
"dtype": "string",
|
164 |
+
"_type": "Value"
|
165 |
+
}
|
166 |
+
}
|
167 |
+
},
|
168 |
+
"homepage": "",
|
169 |
+
"license": ""
|
170 |
+
}
|
examples/ASR/Common-Voice-15-En-Test/sample_0.wav
ADDED
Binary file (202 kB). View file
|
|
examples/ASR/Common-Voice-15-En-Test/sample_1.wav
ADDED
Binary file (118 kB). View file
|
|
examples/ASR/Common-Voice-15-En-Test/sample_2.wav
ADDED
Binary file (214 kB). View file
|
|
examples/ASR/Common-Voice-15-En-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "30218d56801da2e8",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASR/Earnings21-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33dce5920f131621276ca79ef824fc52d5d5bb043d7672458fdbe037c7fb60fd
|
3 |
+
size 310572568
|
examples/ASR/Earnings21-Test/dataset_info.json
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"context": {
|
6 |
+
"text": {
|
7 |
+
"dtype": "string",
|
8 |
+
"_type": "Value"
|
9 |
+
},
|
10 |
+
"audio": {
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"_type": "Audio"
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"instruction": {
|
16 |
+
"audio": {
|
17 |
+
"dtype": "null",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"text": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"answer": {
|
26 |
+
"audio": {
|
27 |
+
"dtype": "null",
|
28 |
+
"_type": "Value"
|
29 |
+
},
|
30 |
+
"text": {
|
31 |
+
"dtype": "string",
|
32 |
+
"_type": "Value"
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"other_attributes": {
|
36 |
+
"id": {
|
37 |
+
"dtype": "string",
|
38 |
+
"_type": "Value"
|
39 |
+
}
|
40 |
+
},
|
41 |
+
"salmonn_7b": {
|
42 |
+
"answer": {
|
43 |
+
"dtype": "string",
|
44 |
+
"_type": "Value"
|
45 |
+
},
|
46 |
+
"model_prediction": {
|
47 |
+
"dtype": "string",
|
48 |
+
"_type": "Value"
|
49 |
+
},
|
50 |
+
"task_type": {
|
51 |
+
"dtype": "string",
|
52 |
+
"_type": "Value"
|
53 |
+
},
|
54 |
+
"text": {
|
55 |
+
"dtype": "string",
|
56 |
+
"_type": "Value"
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"wavllm_fairseq": {
|
60 |
+
"answer": {
|
61 |
+
"dtype": "string",
|
62 |
+
"_type": "Value"
|
63 |
+
},
|
64 |
+
"model_prediction": {
|
65 |
+
"dtype": "string",
|
66 |
+
"_type": "Value"
|
67 |
+
},
|
68 |
+
"task_type": {
|
69 |
+
"dtype": "string",
|
70 |
+
"_type": "Value"
|
71 |
+
},
|
72 |
+
"text": {
|
73 |
+
"dtype": "string",
|
74 |
+
"_type": "Value"
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"Qwen2-Audio-7B-Instruct": {
|
78 |
+
"answer": {
|
79 |
+
"dtype": "string",
|
80 |
+
"_type": "Value"
|
81 |
+
},
|
82 |
+
"model_prediction": {
|
83 |
+
"dtype": "string",
|
84 |
+
"_type": "Value"
|
85 |
+
},
|
86 |
+
"task_type": {
|
87 |
+
"dtype": "string",
|
88 |
+
"_type": "Value"
|
89 |
+
},
|
90 |
+
"text": {
|
91 |
+
"dtype": "string",
|
92 |
+
"_type": "Value"
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"whisper_large_v3_with_llama_3_8b_instruct": {
|
96 |
+
"answer": {
|
97 |
+
"dtype": "string",
|
98 |
+
"_type": "Value"
|
99 |
+
},
|
100 |
+
"model_prediction": {
|
101 |
+
"dtype": "string",
|
102 |
+
"_type": "Value"
|
103 |
+
},
|
104 |
+
"task_type": {
|
105 |
+
"dtype": "string",
|
106 |
+
"_type": "Value"
|
107 |
+
},
|
108 |
+
"text": {
|
109 |
+
"dtype": "string",
|
110 |
+
"_type": "Value"
|
111 |
+
}
|
112 |
+
},
|
113 |
+
"qwen_audio_chat": {
|
114 |
+
"answer": {
|
115 |
+
"dtype": "string",
|
116 |
+
"_type": "Value"
|
117 |
+
},
|
118 |
+
"model_prediction": {
|
119 |
+
"dtype": "string",
|
120 |
+
"_type": "Value"
|
121 |
+
},
|
122 |
+
"task_type": {
|
123 |
+
"dtype": "string",
|
124 |
+
"_type": "Value"
|
125 |
+
},
|
126 |
+
"text": {
|
127 |
+
"dtype": "string",
|
128 |
+
"_type": "Value"
|
129 |
+
}
|
130 |
+
}
|
131 |
+
},
|
132 |
+
"homepage": "",
|
133 |
+
"license": ""
|
134 |
+
}
|
examples/ASR/Earnings21-Test/sample_0.wav
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8e88eccc61c5e8a5e62867c52a8ccfc4e108a5f48459f7df0eb1e9ae7f16d4f
|
3 |
+
size 139072236
|
examples/ASR/Earnings21-Test/sample_1.wav
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcd3ce7847b7fb0f600bb3faeca3cd2a8f4992fd1de17bd831ef6ccfb2623f33
|
3 |
+
size 55065644
|
examples/ASR/Earnings21-Test/sample_2.wav
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:607725d2a33f206a0f00668f1907f4d997fc7dbe7d1e1f9c82045496412bd8bd
|
3 |
+
size 115039268
|
examples/ASR/Earnings21-Test/state.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "2e3dea299b387757",
|
8 |
+
"_format_columns": [
|
9 |
+
"context",
|
10 |
+
"instruction",
|
11 |
+
"answer",
|
12 |
+
"other_attributes",
|
13 |
+
"salmonn_7b",
|
14 |
+
"wavllm_fairseq",
|
15 |
+
"Qwen2-Audio-7B-Instruct",
|
16 |
+
"whisper_large_v3_with_llama_3_8b_instruct",
|
17 |
+
"qwen_audio_chat"
|
18 |
+
],
|
19 |
+
"_format_kwargs": {},
|
20 |
+
"_format_type": null,
|
21 |
+
"_output_all_columns": false,
|
22 |
+
"_split": null
|
23 |
+
}
|
examples/ASR/Earnings22-Test/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51a45b6f2b6f1eaefc76f48f4778b5d5d46793e0a0fc846b1c2dd4b639dd173f
|
3 |
+
size 299513312
|