Sota Model

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Enpas/Whisper-A100s2",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "pad_token_id": 50257,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e193542a5a4c419468b5b8322d59c6b67d4121431c9a5d0b0dcf5b71132fa02
+size 966995080

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c648689fe53391919eddf90b61db29609e924b414725c170b59ece45e8c67a
+size 1925064044

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
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7390a97272fd34ae2743a8936ae540c10a5a09dd1c8c13b2c4687c1e399aaa
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b51538e95c7bf7201db50325ce28d1bf46d9f99249c717bfdd39186a7062137
+size 1064

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 61.04375329467581,
+  "best_model_checkpoint": "./finam2/checkpoint-500",
+  "epoch": 7.246376811594203,
+  "eval_steps": 250,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 94431.8984375,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1608,
+      "step": 100
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 82763.5,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0404,
+      "step": 200
+    },
+    {
+      "epoch": 3.6231884057971016,
+      "eval_loss": 0.016866113990545273,
+      "eval_runtime": 160.3369,
+      "eval_samples_per_second": 1.279,
+      "eval_steps_per_second": 0.162,
+      "eval_wer": 87.55930416447022,
+      "step": 250
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 53642.96875,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.0116,
+      "step": 300
+    },
+    {
+      "epoch": 5.797101449275362,
+      "grad_norm": 53491.53125,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0059,
+      "step": 400
+    },
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 24437.5546875,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.0035,
+      "step": 500
+    },
+    {
+      "epoch": 7.246376811594203,
+      "eval_loss": 0.0023117074742913246,
+      "eval_runtime": 186.2811,
+      "eval_samples_per_second": 1.1,
+      "eval_steps_per_second": 0.14,
+      "eval_wer": 61.04375329467581,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.60322572050432e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1607df3c13c77b7cf152752dd6963a5ec9e74cda0b128fab79c0d723fb1926
+size 5368