Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,152 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "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": 448,
+  "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,
+  "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,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50360,
+    50361,
+    50362
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4aa598c0e1c5a1b95cf742beec8563dff9efb1444a34234f26c339e0c126879
+size 967102729

runs/Aug29_23-31-05_arkark/events.out.tfevents.1693366271.arkark

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700fef95d64d2c997bd4d887cf9a03a2c2fd2bf33b71f47e7099fde7b39d5dec
+size 13349

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "|BOS|",
+  "eos_token": "|EOS|",
+  "pad_token": "|PAD|"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "|BOS|",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "|EOS|",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "|PAD|",
+  "processor_class": "WhisperProcessor",
+  "tokenizer_class": "PhonemeTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2866d5a2fb8356a6ac8511598d598e1aff9f77a2b20b6ffb3012bfda61004680
+size 4155

vocab.txt

@@ -0,0 +1,57 @@
+o	0
+æ	1
+J	2
+P	3
+s	4
+ʒ	5
+ɑ	6
+ʌ	7
+ɛ	8
+ʔ	9
+ɔ	10
+t	11
+θ	12
+̍	13
+ɹ	14
+v	15
+W	16
+p	17
+i	18
+ɡ	19
+S	20
+ɨ	21
+ɦ	22
+m	23
+b	24
+w	25
+̩	26
+g	27
+ʃ	28
+C	29
+l	30
+̃	31
+̥	32
+ɚ	33
+ŋ	34
+ð	35
+ə	36
+n	37
+u	38
+d	39
+f	40
+ɪ	41
+k	42
+O	43
+ʉ	44
+ɝ	45
+h	46
+̚	47
+z	48
+ʊ	49
+e	50
+Y	51
+j	52
+ɾ	53
+|EOS|	54
+|BOS|	55
+|PAD|	56