Upload model files

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "Enpas/Shukv2",
+  "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": 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": 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": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,22 @@
+{
+  "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",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ed1308b0197b664afafb89a324c964fe1a9b13d8c0f169503cc8a5884da0c2
+size 966995080

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b934b418ef4ab7a7360fe2ce1e5cd08221e8ad6b463fbc828c3d356e84195b
+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 sha256:3540179bbcfe2a2e55d05fad49c806615d68122d33b057e8a5ff20ca08833829
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49054e3b5dea463b82349ae8b05bc44c24728fc8e9d56eee16e9fedd96e927d4
+size 1064

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": 85.87243015287297,
+  "best_model_checkpoint": "./Shukv4/checkpoint-500",
+  "epoch": 2.688172043010753,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13440860215053763,
+      "grad_norm": 349994.25,
+      "learning_rate": 3.125e-06,
+      "loss": 0.5555,
+      "step": 25
+    },
+    {
+      "epoch": 0.26881720430107525,
+      "grad_norm": 296199.8125,
+      "learning_rate": 6.25e-06,
+      "loss": 0.3776,
+      "step": 50
+    },
+    {
+      "epoch": 0.4032258064516129,
+      "grad_norm": 218550.265625,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.286,
+      "step": 75
+    },
+    {
+      "epoch": 0.5376344086021505,
+      "grad_norm": 241839.0,
+      "learning_rate": 1.25e-05,
+      "loss": 0.2629,
+      "step": 100
+    },
+    {
+      "epoch": 0.6720430107526881,
+      "grad_norm": 224651.953125,
+      "learning_rate": 1.2152777777777779e-05,
+      "loss": 0.2473,
+      "step": 125
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 247373.3125,
+      "learning_rate": 1.1805555555555555e-05,
+      "loss": 0.2225,
+      "step": 150
+    },
+    {
+      "epoch": 0.9408602150537635,
+      "grad_norm": 232539.5,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 0.1814,
+      "step": 175
+    },
+    {
+      "epoch": 1.075268817204301,
+      "grad_norm": 208122.359375,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1379,
+      "step": 200
+    },
+    {
+      "epoch": 1.2096774193548387,
+      "grad_norm": 203154.734375,
+      "learning_rate": 1.076388888888889e-05,
+      "loss": 0.0926,
+      "step": 225
+    },
+    {
+      "epoch": 1.3440860215053765,
+      "grad_norm": 193545.453125,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 0.0877,
+      "step": 250
+    },
+    {
+      "epoch": 1.478494623655914,
+      "grad_norm": 159916.4375,
+      "learning_rate": 1.0069444444444445e-05,
+      "loss": 0.0759,
+      "step": 275
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 203974.796875,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.0886,
+      "step": 300
+    },
+    {
+      "epoch": 1.7473118279569892,
+      "grad_norm": 176038.296875,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.0809,
+      "step": 325
+    },
+    {
+      "epoch": 1.881720430107527,
+      "grad_norm": 156732.640625,
+      "learning_rate": 9.027777777777777e-06,
+      "loss": 0.0598,
+      "step": 350
+    },
+    {
+      "epoch": 2.0161290322580645,
+      "grad_norm": 116201.7734375,
+      "learning_rate": 8.680555555555556e-06,
+      "loss": 0.0546,
+      "step": 375
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 81153.625,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0281,
+      "step": 400
+    },
+    {
+      "epoch": 2.28494623655914,
+      "grad_norm": 95937.9765625,
+      "learning_rate": 7.98611111111111e-06,
+      "loss": 0.0328,
+      "step": 425
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 105021.359375,
+      "learning_rate": 7.63888888888889e-06,
+      "loss": 0.0271,
+      "step": 450
+    },
+    {
+      "epoch": 2.553763440860215,
+      "grad_norm": 73798.6796875,
+      "learning_rate": 7.2916666666666674e-06,
+      "loss": 0.0317,
+      "step": 475
+    },
+    {
+      "epoch": 2.688172043010753,
+      "grad_norm": 111273.5546875,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 0.0286,
+      "step": 500
+    },
+    {
+      "epoch": 2.688172043010753,
+      "eval_loss": 0.032379038631916046,
+      "eval_runtime": 903.1767,
+      "eval_samples_per_second": 0.227,
+      "eval_steps_per_second": 0.029,
+      "eval_wer": 85.87243015287297,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.72804937711616e+18,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8028a017a4460498ab21ed36604550dd2e3d30a0d4602d90806db216e3f5f7
+size 5368