Training in progress, epoch 0

config.json

@@ -1,116 +1,45 @@
 {
-  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
-  "activation_dropout": 0.05,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
+  "_name_or_path": "distil-whisper/distil-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "WhisperForAudioClassification"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
-  "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
-  ],
-  "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
-  ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.05,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.05,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 2,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "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_min_space": 1,
-  "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
-  "mask_time_selection": "static",
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
-  "num_attention_heads": 16,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
-  "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 0,
-  "proj_codevector_dim": 256,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.45.1",
+  "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 33,
-  "xvector_output_dim": 512
+  "vocab_size": 51866
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f724710ebfb2857517a089699d0a8557d3ca14637913aa1f67a8003fbf168ea
-size 1262859296
+oid sha256:521aa337faa597864f55f4f985d982d7a8664a4995e8516b552ee4a2fe64cdf0
+size 2549244064

preprocessor_config.json

@@ -1,10 +1,14 @@
 {
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
   "padding_side": "right",
   "padding_value": 0.0,
-  "processor_class": "Wav2Vec2ProcessorWithLM",
-  "return_attention_mask": true,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

runs/Oct11_00-59-46_LCND3341981/events.out.tfevents.1728570588.LCND3341981.26660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68063d0aa4fae5af88e24f1965fefdabeaf8ac5ff74ffdc2709c11a86864a67e
+size 5577

runs/Oct11_01-04-28_LCND3341981/events.out.tfevents.1728570868.LCND3341981.47000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e109a9eebd11349f6f421b3f4704426b014a733bd381755eb8d4750742883d20
+size 5576

runs/Oct11_12-45-42_LCND3341981/events.out.tfevents.1728612944.LCND3341981.26060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e846e72d6f13c7746f647a96435c5b7530552f0fe3bf3b86862b2f94ea272570
+size 5576

runs/Oct11_13-29-58_LCND3341981/events.out.tfevents.1728615598.LCND3341981.37168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505e0b8fa717e6d8b380c3960a1cc177003feb38ea5d507b8a6808e6c77cba61
+size 6199

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f6fbf6fb3c6821fc50213eefc2e29ad3ebc8be7922525abf8d479e7612e94f
+oid sha256:d4bc67dc1e58e6faed1fe433c0690017608406792de157cd607cb223fa70ce2e
 size 5304