Training in progress, step 100

config.json

@@ -1,52 +1,52 @@
-{
-  "_name_or_path": "openai/whisper-medium",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": false,
-  "architectures": [
-    "WhisperForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "classifier_proj_size": 256,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 24,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 24,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": null,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
-  "max_length": 448,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "median_filter_width": 7,
-  "model_type": "whisper",
-  "num_hidden_layers": 24,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
-  "suppress_tokens": [],
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51865
-}
+{
+  "_name_or_path": "openai/whisper-medium",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 24,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6df563729b07ec87f718136757673dec3eaa401c6644d378f9920dc5187b56d
+oid sha256:65ad9a75f1bcfd14cb2410dc615397dfda09093f38bbe08e55520e03f5ba7828
 size 3055544304

preprocessor_config.json

@@ -1,14 +1,14 @@
-{
-  "chunk_length": 30,
-  "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 80,
-  "hop_length": 160,
-  "n_fft": 400,
-  "n_samples": 480000,
-  "nb_max_frames": 3000,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "processor_class": "WhisperProcessor",
-  "return_attention_mask": false,
-  "sampling_rate": 16000
-}
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Jul09_21-42-33_DESKTOP-0Q1NC6M/events.out.tfevents.1720572165.DESKTOP-0Q1NC6M.6300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732fe6381c3d9dc0c025631c6eb8e22e741d19bed9cc6bde9a29aa0aaa06a474
+size 6869

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fbea228dbb249ccad9c137462f252d0ab9ffec5f279af79b68d0ecc8279ca54
-size 5240
+oid sha256:ac8f4c4bccc5aa29969a2758e85fb8975642eaa6471b37ebca00e968defa66c4
+size 5304