Training in progress, step 1000

config.json

@@ -109,6 +109,7 @@
     "AutoModelForSpeechSeq2Seq": "asr_modeling.ASRModel",
     "AutoProcessor": "asr_processing.ASRProcessor"
   },
+  "bos_token_id": null,
   "custom_pipelines": {
     "automatic-speech-recognition": {
       "impl": "asr_pipeline.ASRPipeline",
@@ -233,6 +234,7 @@
     ]
   ],
   "encoder_dim": 1280,
+  "eos_token_id": 151645,
   "freeze_projector": false,
   "freq_mask_length": 27,
   "inference_warmup_tokens": 10,
@@ -261,10 +263,11 @@
   "num_experts_per_tok": 2,
   "num_freq_masks": 2,
   "num_time_masks": 2,
+  "pad_token_id": 151643,
   "pipeline_tag": "automatic-speech-recognition",
   "pretrained_model_path": "mazesmazes/tiny-audio-embedded",
   "projector_dropout": 0.0,
-  "projector_hidden_dim": 1024,
+  "projector_hidden_dim": 2048,
   "projector_init_std": 0.02,
   "projector_num_layers": 2,
   "projector_pool_stride": 4,
@@ -345,7 +348,7 @@
   "time_mask_length": 100,
   "top_k": null,
   "top_p": null,
-  "transformers_version": "5.6.0",
+  "transformers_version": "5.6.1",
   "use_cache": false,
   "use_lora": false,
   "use_specaugment": true,

generation_config.json

@@ -1,7 +1,7 @@
 {
-  "bos_token_id": 151643,
   "do_sample": false,
   "eos_token_id": [
+    151645,
     151645,
     151643
   ],
@@ -12,6 +12,6 @@
   "num_beams": 1,
   "pad_token_id": 151643,
   "repetition_penalty": 1.0,
-  "transformers_version": "5.6.0",
+  "transformers_version": "5.6.1",
   "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b77a4836aeb06d6628aacbc351f8fce90ee6ce974d4ec3b7c5fb37f7707297b
-size 12585288
+oid sha256:8b585115f1d859ba9b44715ee8e76780fe646af0a8e09cd0b6f436f3589e4c01
+size 25170248

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb18fa029dd1c46ae835bb3aa2c1aa8c1ada5d7dbb158a927ed0a51f7a0f96d2
-size 5329
+oid sha256:5cc9bfda4771472567bcfaea90ff6cd04d39858722812e63aee0c83bf086c440
+size 5393