Upload trained model

additional_decoder_block.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198def521215c52aeb9e7335bbdb28d48540dcae5c0c174b08049e6e3b52b52a
+size 37809834

classifier.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebcb2604d12f63ecc15d5bab8cefe508bf150fed8ccf0b36fd5fc8995afcd9b
+size 4739176

config.json

@@ -0,0 +1,48 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperWithExtraDecoderAndClassifier"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50256,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50257,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50256,
+  "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_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50257,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.45.2"
+}

log_eval.txt

@@ -0,0 +1 @@
+{"eval_accuracy": 0.22032726434662364, "eval_precision": 0.12059765208110992, "eval_recall": 0.8385899814471243, "eval_f1": 0.21087007231163984}{"eval_accuracy": 0.9057692307692308, "eval_precision": 0.6382978723404256, "eval_recall": 0.4838709677419355, "eval_f1": 0.5504587155963303}{"eval_accuracy": 0.9461538461538461, "eval_precision": 0.7931034482758621, "eval_recall": 0.7419354838709677, "eval_f1": 0.7666666666666667}{"eval_accuracy": 0.8826923076923077, "eval_precision": 0.5053763440860215, "eval_recall": 0.7580645161290323, "eval_f1": 0.6064516129032258}{"eval_accuracy": 0.9288461538461539, "eval_precision": 0.7906976744186046, "eval_recall": 0.5483870967741935, "eval_f1": 0.6476190476190476}{"eval_accuracy": 0.9346153846153846, "eval_precision": 0.7258064516129032, "eval_recall": 0.7258064516129032, "eval_f1": 0.7258064516129032}{"eval_accuracy": 0.9403846153846154, "eval_precision": 0.7719298245614035, "eval_recall": 0.7096774193548387, "eval_f1": 0.7394957983193278}{"eval_accuracy": 0.9423076923076923, "eval_precision": 0.7962962962962963, "eval_recall": 0.6935483870967742, "eval_f1": 0.7413793103448276}{"eval_accuracy": 0.9423076923076923, "eval_precision": 0.7962962962962963, "eval_recall": 0.6935483870967742, "eval_f1": 0.7413793103448276}{"eval_accuracy": 0.9280940308826918, "eval_precision": 0.8179271708683473, "eval_recall": 0.5417439703153989, "eval_f1": 0.6517857142857143}

log_eval_word_level.txt

@@ -0,0 +1 @@
+"Evaluate at WORD LEVEL:"{"eval_accuracy": 0.26597014925373136, "eval_precision": 0.14696370822853036, "eval_recall": 0.8279352226720648, "eval_f1": 0.24961855355508086}"Evaluate at WORD LEVEL:"{"eval_accuracy": 0.9188059701492537, "eval_precision": 0.8245614035087719, "eval_recall": 0.5708502024291497, "eval_f1": 0.6746411483253588}

preprocessor_config.json

@@ -0,0 +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
+}

runs/Jan28_04-07-30_isl-gpu43/events.out.tfevents.1738066100.isl-gpu43.2836202.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a272b4a909abd0071fe9e15f5a2f5f00eadbb43b0a6bb9ac2eb15f8e1fb813
+size 11404

runs/Jan28_04-07-30_isl-gpu43/events.out.tfevents.1738066363.isl-gpu43.2836202.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a0d3afd42012cbe3a5d1eeded3ef60e34a4e5f1c50d3bf90ab1c82e2618f47
+size 590

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4eb66cdb79b0b8227f481caccf361dbc590033a281b0b478b3588784c60019
+size 5496

training_args.json

@@ -0,0 +1 @@
+{"output_dir": "trained_models/whisper-small_expresso_final_before_gpt_2025_01_28__04_07_30", "overwrite_output_dir": true, "do_train": true, "do_eval": true, "do_predict": false, "eval_strategy": "steps", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 4, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0, "torch_empty_cache_steps": null, "learning_rate": 0.0005, "weight_decay": 0.01, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 2, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.05, "warmup_steps": 0, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "trained_models/whisper-small_expresso_final_before_gpt_2025_01_28__04_07_30/runs/Jan28_04-07-30_isl-gpu43", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 100, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 20, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "trained_models/whisper-small_expresso_final_before_gpt_2025_01_28__04_07_30", "disable_tqdm": false, "remove_unused_columns": true, "label_names": ["labels_head", "whisper_labels", "sentence_index"], "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": {"split_batches": false, "dispatch_batches": null, "even_batches": true, "use_seedable_sampler": true, "non_blocking": false, "gradient_accumulation_kwargs": null}, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard", "wandb"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": null, "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false, "eval_on_start": false, "use_liger_kernel": false, "eval_use_gather_object": false, "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": 96, "generation_num_beams": null, "generation_config": null}