Upload 8 files

config.json

@@ -0,0 +1,164 @@
+{
+  "_name_or_path": "openai/whisper-base.en",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50257,
+  "dropout": 0.9,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50256,
+  "forced_decoder_ids": [
+    [
+      1,
+      50362
+    ]
+  ],
+  "id2label": {
+    "0": "NoStutteredWords",
+    "1": "WordRep",
+    "2": "SoundRep",
+    "3": "Prolongation",
+    "4": "Interjection",
+    "5": "Block"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Block": 5,
+    "Interjection": 4,
+    "NoStutteredWords": 0,
+    "Prolongation": 3,
+    "SoundRep": 2,
+    "WordRep": 1
+  },
+  "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": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
+    50358,
+    50359,
+    50360,
+    50361
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51864
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8c4455a0f97089bd4e56761f0eca5e4dd4a0c393b2a751001a197ded7294e5
+size 165870947

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 3.0,
+  "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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b03851f954cf1cb74951cf614583e98df7de572b30242023009897a3e4a5bbe
+size 82925687

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdf234bdc48b4ee1ebe2c987f483f5e7dac1f9dd0afaaf17e15768fcc1fbd65
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a82b6eb0c2879a2af3438ce57fec8a4399eb1ab63340856426f3235c2b5ac4b
+size 623

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6411932110786438,
+  "best_model_checkpoint": "G:/My Drive/Thesis-best-model/Whisper_e_base-en-dropout=0.0\\checkpoint-825",
+  "epoch": 2.0,
+  "global_step": 1650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.3484848484848487e-05,
+      "loss": 0.921,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8005087209302325,
+      "eval_f1": 0.7782251233544938,
+      "eval_loss": 0.6411932110786438,
+      "eval_precision": 0.7638742227416849,
+      "eval_recall": 0.8005087209302325,
+      "eval_runtime": 54.6075,
+      "eval_samples_per_second": 50.396,
+      "eval_steps_per_second": 6.3,
+      "step": 825
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.1969696969696972e-05,
+      "loss": 0.5733,
+      "step": 1000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 0.4501,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8135901162790697,
+      "eval_f1": 0.7999960344419578,
+      "eval_loss": 0.6439159512519836,
+      "eval_precision": 0.7974439877300139,
+      "eval_recall": 0.8135901162790697,
+      "eval_runtime": 55.8052,
+      "eval_samples_per_second": 49.314,
+      "eval_steps_per_second": 6.164,
+      "step": 1650
+    }
+  ],
+  "max_steps": 8250,
+  "num_train_epochs": 10,
+  "total_flos": 3.7914100650432e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252d0954d5ff4f565666b1789bd3f377b3c99d93238bcdda34f53d48cd5d7588
+size 4079