Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2") model = AutoModelForSpeechSeq2Seq.from_pretrained("qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2") - Notebooks
- Google Colab
- Kaggle
Quentin Meeus commited on
Commit ·
2b58b15
1
Parent(s): 26d3939
remove old checkpoint
Browse files- checkpoint-200/config.json +0 -185
- checkpoint-200/generation_config.json +0 -263
- checkpoint-200/model.safetensors +0 -3
- checkpoint-200/optimizer.pt +0 -3
- checkpoint-200/preprocessor_config.json +0 -14
- checkpoint-200/rng_state.pth +0 -3
- checkpoint-200/scheduler.pt +0 -3
- checkpoint-200/trainer_state.json +0 -45
- checkpoint-200/training_args.bin +0 -3
checkpoint-200/config.json
DELETED
|
@@ -1,185 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "openai/whisper-small",
|
| 3 |
-
"activation_dropout": 0.0,
|
| 4 |
-
"activation_function": "gelu",
|
| 5 |
-
"adaptor_layernorm": true,
|
| 6 |
-
"apply_spec_augment": false,
|
| 7 |
-
"architectures": [
|
| 8 |
-
"WhisperForConditionalGeneration"
|
| 9 |
-
],
|
| 10 |
-
"attention_dropout": 0.0,
|
| 11 |
-
"begin_suppress_tokens": [
|
| 12 |
-
220,
|
| 13 |
-
50257
|
| 14 |
-
],
|
| 15 |
-
"bos_token_id": 50257,
|
| 16 |
-
"classifier_proj_size": 256,
|
| 17 |
-
"d_model": 768,
|
| 18 |
-
"decoder_attention_heads": 12,
|
| 19 |
-
"decoder_ffn_dim": 3072,
|
| 20 |
-
"decoder_layerdrop": 0.0,
|
| 21 |
-
"decoder_layers": 12,
|
| 22 |
-
"decoder_start_token_id": 50258,
|
| 23 |
-
"dropout": 0.0,
|
| 24 |
-
"encoder_attention_heads": 12,
|
| 25 |
-
"encoder_ffn_dim": 3072,
|
| 26 |
-
"encoder_layerdrop": 0.0,
|
| 27 |
-
"encoder_layers": 12,
|
| 28 |
-
"eos_token_id": 50257,
|
| 29 |
-
"forced_decoder_ids": [
|
| 30 |
-
[
|
| 31 |
-
1,
|
| 32 |
-
50259
|
| 33 |
-
],
|
| 34 |
-
[
|
| 35 |
-
2,
|
| 36 |
-
50359
|
| 37 |
-
],
|
| 38 |
-
[
|
| 39 |
-
3,
|
| 40 |
-
50363
|
| 41 |
-
]
|
| 42 |
-
],
|
| 43 |
-
"init_std": 0.02,
|
| 44 |
-
"is_encoder_decoder": true,
|
| 45 |
-
"mask_feature_length": 10,
|
| 46 |
-
"mask_feature_min_masks": 0,
|
| 47 |
-
"mask_feature_prob": 0.0,
|
| 48 |
-
"mask_time_length": 10,
|
| 49 |
-
"mask_time_min_masks": 2,
|
| 50 |
-
"mask_time_prob": 0.05,
|
| 51 |
-
"max_length": 448,
|
| 52 |
-
"max_source_positions": 1500,
|
| 53 |
-
"max_target_positions": 448,
|
| 54 |
-
"median_filter_width": 7,
|
| 55 |
-
"model_type": "whisper",
|
| 56 |
-
"num_hidden_layers": 12,
|
| 57 |
-
"num_mel_bins": 80,
|
| 58 |
-
"pad_token_id": 50257,
|
| 59 |
-
"scale_embedding": false,
|
| 60 |
-
"slu_attention_heads": 12,
|
| 61 |
-
"slu_dropout": 0.3,
|
| 62 |
-
"slu_embed_dim": 768,
|
| 63 |
-
"slu_focus": 1.0,
|
| 64 |
-
"slu_input_from": "decoder",
|
| 65 |
-
"slu_input_layers": -1,
|
| 66 |
-
"slu_layers": 2,
|
| 67 |
-
"slu_output_dim": 37,
|
| 68 |
-
"slu_weight": 0.2,
|
| 69 |
-
"special_token_ids": [
|
| 70 |
-
50257,
|
| 71 |
-
50258,
|
| 72 |
-
50259,
|
| 73 |
-
50260,
|
| 74 |
-
50261,
|
| 75 |
-
50262,
|
| 76 |
-
50263,
|
| 77 |
-
50264,
|
| 78 |
-
50265,
|
| 79 |
-
50266,
|
| 80 |
-
50267,
|
| 81 |
-
50268,
|
| 82 |
-
50269,
|
| 83 |
-
50270,
|
| 84 |
-
50271,
|
| 85 |
-
50272,
|
| 86 |
-
50273,
|
| 87 |
-
50274,
|
| 88 |
-
50275,
|
| 89 |
-
50276,
|
| 90 |
-
50277,
|
| 91 |
-
50278,
|
| 92 |
-
50279,
|
| 93 |
-
50280,
|
| 94 |
-
50281,
|
| 95 |
-
50282,
|
| 96 |
-
50283,
|
| 97 |
-
50284,
|
| 98 |
-
50285,
|
| 99 |
-
50286,
|
| 100 |
-
50287,
|
| 101 |
-
50288,
|
| 102 |
-
50289,
|
| 103 |
-
50290,
|
| 104 |
-
50291,
|
| 105 |
-
50292,
|
| 106 |
-
50293,
|
| 107 |
-
50294,
|
| 108 |
-
50295,
|
| 109 |
-
50296,
|
| 110 |
-
50297,
|
| 111 |
-
50298,
|
| 112 |
-
50299,
|
| 113 |
-
50300,
|
| 114 |
-
50301,
|
| 115 |
-
50302,
|
| 116 |
-
50303,
|
| 117 |
-
50304,
|
| 118 |
-
50305,
|
| 119 |
-
50306,
|
| 120 |
-
50307,
|
| 121 |
-
50308,
|
| 122 |
-
50309,
|
| 123 |
-
50310,
|
| 124 |
-
50311,
|
| 125 |
-
50312,
|
| 126 |
-
50313,
|
| 127 |
-
50314,
|
| 128 |
-
50315,
|
| 129 |
-
50316,
|
| 130 |
-
50317,
|
| 131 |
-
50318,
|
| 132 |
-
50319,
|
| 133 |
-
50320,
|
| 134 |
-
50321,
|
| 135 |
-
50322,
|
| 136 |
-
50323,
|
| 137 |
-
50324,
|
| 138 |
-
50325,
|
| 139 |
-
50326,
|
| 140 |
-
50327,
|
| 141 |
-
50328,
|
| 142 |
-
50329,
|
| 143 |
-
50330,
|
| 144 |
-
50331,
|
| 145 |
-
50332,
|
| 146 |
-
50333,
|
| 147 |
-
50334,
|
| 148 |
-
50335,
|
| 149 |
-
50336,
|
| 150 |
-
50337,
|
| 151 |
-
50338,
|
| 152 |
-
50339,
|
| 153 |
-
50340,
|
| 154 |
-
50341,
|
| 155 |
-
50342,
|
| 156 |
-
50343,
|
| 157 |
-
50344,
|
| 158 |
-
50345,
|
| 159 |
-
50346,
|
| 160 |
-
50347,
|
| 161 |
-
50348,
|
| 162 |
-
50349,
|
| 163 |
-
50350,
|
| 164 |
-
50351,
|
| 165 |
-
50352,
|
| 166 |
-
50353,
|
| 167 |
-
50354,
|
| 168 |
-
50355,
|
| 169 |
-
50356,
|
| 170 |
-
50357,
|
| 171 |
-
50358,
|
| 172 |
-
50359,
|
| 173 |
-
50360,
|
| 174 |
-
50361,
|
| 175 |
-
50362,
|
| 176 |
-
50363
|
| 177 |
-
],
|
| 178 |
-
"task": "token_classification",
|
| 179 |
-
"torch_dtype": "float32",
|
| 180 |
-
"transformers_version": "4.37.0.dev0",
|
| 181 |
-
"use_cache": true,
|
| 182 |
-
"use_crf": false,
|
| 183 |
-
"use_weighted_layer_sum": false,
|
| 184 |
-
"vocab_size": 51885
|
| 185 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/generation_config.json
DELETED
|
@@ -1,263 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alignment_heads": [
|
| 3 |
-
[
|
| 4 |
-
5,
|
| 5 |
-
3
|
| 6 |
-
],
|
| 7 |
-
[
|
| 8 |
-
5,
|
| 9 |
-
9
|
| 10 |
-
],
|
| 11 |
-
[
|
| 12 |
-
8,
|
| 13 |
-
0
|
| 14 |
-
],
|
| 15 |
-
[
|
| 16 |
-
8,
|
| 17 |
-
4
|
| 18 |
-
],
|
| 19 |
-
[
|
| 20 |
-
8,
|
| 21 |
-
7
|
| 22 |
-
],
|
| 23 |
-
[
|
| 24 |
-
8,
|
| 25 |
-
8
|
| 26 |
-
],
|
| 27 |
-
[
|
| 28 |
-
9,
|
| 29 |
-
0
|
| 30 |
-
],
|
| 31 |
-
[
|
| 32 |
-
9,
|
| 33 |
-
7
|
| 34 |
-
],
|
| 35 |
-
[
|
| 36 |
-
9,
|
| 37 |
-
9
|
| 38 |
-
],
|
| 39 |
-
[
|
| 40 |
-
10,
|
| 41 |
-
5
|
| 42 |
-
]
|
| 43 |
-
],
|
| 44 |
-
"begin_suppress_tokens": [
|
| 45 |
-
220,
|
| 46 |
-
50257
|
| 47 |
-
],
|
| 48 |
-
"bos_token_id": 50257,
|
| 49 |
-
"decoder_start_token_id": 50258,
|
| 50 |
-
"eos_token_id": 50257,
|
| 51 |
-
"forced_decoder_ids": [
|
| 52 |
-
[
|
| 53 |
-
1,
|
| 54 |
-
null
|
| 55 |
-
],
|
| 56 |
-
[
|
| 57 |
-
2,
|
| 58 |
-
50359
|
| 59 |
-
]
|
| 60 |
-
],
|
| 61 |
-
"is_multilingual": true,
|
| 62 |
-
"lang_to_id": {
|
| 63 |
-
"<|af|>": 50327,
|
| 64 |
-
"<|am|>": 50334,
|
| 65 |
-
"<|ar|>": 50272,
|
| 66 |
-
"<|as|>": 50350,
|
| 67 |
-
"<|az|>": 50304,
|
| 68 |
-
"<|ba|>": 50355,
|
| 69 |
-
"<|be|>": 50330,
|
| 70 |
-
"<|bg|>": 50292,
|
| 71 |
-
"<|bn|>": 50302,
|
| 72 |
-
"<|bo|>": 50347,
|
| 73 |
-
"<|br|>": 50309,
|
| 74 |
-
"<|bs|>": 50315,
|
| 75 |
-
"<|ca|>": 50270,
|
| 76 |
-
"<|cs|>": 50283,
|
| 77 |
-
"<|cy|>": 50297,
|
| 78 |
-
"<|da|>": 50285,
|
| 79 |
-
"<|de|>": 50261,
|
| 80 |
-
"<|el|>": 50281,
|
| 81 |
-
"<|en|>": 50259,
|
| 82 |
-
"<|es|>": 50262,
|
| 83 |
-
"<|et|>": 50307,
|
| 84 |
-
"<|eu|>": 50310,
|
| 85 |
-
"<|fa|>": 50300,
|
| 86 |
-
"<|fi|>": 50277,
|
| 87 |
-
"<|fo|>": 50338,
|
| 88 |
-
"<|fr|>": 50265,
|
| 89 |
-
"<|gl|>": 50319,
|
| 90 |
-
"<|gu|>": 50333,
|
| 91 |
-
"<|haw|>": 50352,
|
| 92 |
-
"<|ha|>": 50354,
|
| 93 |
-
"<|he|>": 50279,
|
| 94 |
-
"<|hi|>": 50276,
|
| 95 |
-
"<|hr|>": 50291,
|
| 96 |
-
"<|ht|>": 50339,
|
| 97 |
-
"<|hu|>": 50286,
|
| 98 |
-
"<|hy|>": 50312,
|
| 99 |
-
"<|id|>": 50275,
|
| 100 |
-
"<|is|>": 50311,
|
| 101 |
-
"<|it|>": 50274,
|
| 102 |
-
"<|ja|>": 50266,
|
| 103 |
-
"<|jw|>": 50356,
|
| 104 |
-
"<|ka|>": 50329,
|
| 105 |
-
"<|kk|>": 50316,
|
| 106 |
-
"<|km|>": 50323,
|
| 107 |
-
"<|kn|>": 50306,
|
| 108 |
-
"<|ko|>": 50264,
|
| 109 |
-
"<|la|>": 50294,
|
| 110 |
-
"<|lb|>": 50345,
|
| 111 |
-
"<|ln|>": 50353,
|
| 112 |
-
"<|lo|>": 50336,
|
| 113 |
-
"<|lt|>": 50293,
|
| 114 |
-
"<|lv|>": 50301,
|
| 115 |
-
"<|mg|>": 50349,
|
| 116 |
-
"<|mi|>": 50295,
|
| 117 |
-
"<|mk|>": 50308,
|
| 118 |
-
"<|ml|>": 50296,
|
| 119 |
-
"<|mn|>": 50314,
|
| 120 |
-
"<|mr|>": 50320,
|
| 121 |
-
"<|ms|>": 50282,
|
| 122 |
-
"<|mt|>": 50343,
|
| 123 |
-
"<|my|>": 50346,
|
| 124 |
-
"<|ne|>": 50313,
|
| 125 |
-
"<|nl|>": 50271,
|
| 126 |
-
"<|nn|>": 50342,
|
| 127 |
-
"<|no|>": 50288,
|
| 128 |
-
"<|oc|>": 50328,
|
| 129 |
-
"<|pa|>": 50321,
|
| 130 |
-
"<|pl|>": 50269,
|
| 131 |
-
"<|ps|>": 50340,
|
| 132 |
-
"<|pt|>": 50267,
|
| 133 |
-
"<|ro|>": 50284,
|
| 134 |
-
"<|ru|>": 50263,
|
| 135 |
-
"<|sa|>": 50344,
|
| 136 |
-
"<|sd|>": 50332,
|
| 137 |
-
"<|si|>": 50322,
|
| 138 |
-
"<|sk|>": 50298,
|
| 139 |
-
"<|sl|>": 50305,
|
| 140 |
-
"<|sn|>": 50324,
|
| 141 |
-
"<|so|>": 50326,
|
| 142 |
-
"<|sq|>": 50317,
|
| 143 |
-
"<|sr|>": 50303,
|
| 144 |
-
"<|su|>": 50357,
|
| 145 |
-
"<|sv|>": 50273,
|
| 146 |
-
"<|sw|>": 50318,
|
| 147 |
-
"<|ta|>": 50287,
|
| 148 |
-
"<|te|>": 50299,
|
| 149 |
-
"<|tg|>": 50331,
|
| 150 |
-
"<|th|>": 50289,
|
| 151 |
-
"<|tk|>": 50341,
|
| 152 |
-
"<|tl|>": 50348,
|
| 153 |
-
"<|tr|>": 50268,
|
| 154 |
-
"<|tt|>": 50351,
|
| 155 |
-
"<|uk|>": 50280,
|
| 156 |
-
"<|ur|>": 50290,
|
| 157 |
-
"<|uz|>": 50337,
|
| 158 |
-
"<|vi|>": 50278,
|
| 159 |
-
"<|yi|>": 50335,
|
| 160 |
-
"<|yo|>": 50325,
|
| 161 |
-
"<|zh|>": 50260
|
| 162 |
-
},
|
| 163 |
-
"max_initial_timestamp_index": 1,
|
| 164 |
-
"max_length": 448,
|
| 165 |
-
"no_timestamps_token_id": 50363,
|
| 166 |
-
"pad_token_id": 50257,
|
| 167 |
-
"return_timestamps": false,
|
| 168 |
-
"suppress_tokens": [
|
| 169 |
-
1,
|
| 170 |
-
2,
|
| 171 |
-
7,
|
| 172 |
-
8,
|
| 173 |
-
9,
|
| 174 |
-
10,
|
| 175 |
-
14,
|
| 176 |
-
25,
|
| 177 |
-
26,
|
| 178 |
-
27,
|
| 179 |
-
28,
|
| 180 |
-
29,
|
| 181 |
-
31,
|
| 182 |
-
58,
|
| 183 |
-
59,
|
| 184 |
-
60,
|
| 185 |
-
61,
|
| 186 |
-
62,
|
| 187 |
-
63,
|
| 188 |
-
90,
|
| 189 |
-
91,
|
| 190 |
-
92,
|
| 191 |
-
93,
|
| 192 |
-
359,
|
| 193 |
-
503,
|
| 194 |
-
522,
|
| 195 |
-
542,
|
| 196 |
-
873,
|
| 197 |
-
893,
|
| 198 |
-
902,
|
| 199 |
-
918,
|
| 200 |
-
922,
|
| 201 |
-
931,
|
| 202 |
-
1350,
|
| 203 |
-
1853,
|
| 204 |
-
1982,
|
| 205 |
-
2460,
|
| 206 |
-
2627,
|
| 207 |
-
3246,
|
| 208 |
-
3253,
|
| 209 |
-
3268,
|
| 210 |
-
3536,
|
| 211 |
-
3846,
|
| 212 |
-
3961,
|
| 213 |
-
4183,
|
| 214 |
-
4667,
|
| 215 |
-
6585,
|
| 216 |
-
6647,
|
| 217 |
-
7273,
|
| 218 |
-
9061,
|
| 219 |
-
9383,
|
| 220 |
-
10428,
|
| 221 |
-
10929,
|
| 222 |
-
11938,
|
| 223 |
-
12033,
|
| 224 |
-
12331,
|
| 225 |
-
12562,
|
| 226 |
-
13793,
|
| 227 |
-
14157,
|
| 228 |
-
14635,
|
| 229 |
-
15265,
|
| 230 |
-
15618,
|
| 231 |
-
16553,
|
| 232 |
-
16604,
|
| 233 |
-
18362,
|
| 234 |
-
18956,
|
| 235 |
-
20075,
|
| 236 |
-
21675,
|
| 237 |
-
22520,
|
| 238 |
-
26130,
|
| 239 |
-
26161,
|
| 240 |
-
26435,
|
| 241 |
-
28279,
|
| 242 |
-
29464,
|
| 243 |
-
31650,
|
| 244 |
-
32302,
|
| 245 |
-
32470,
|
| 246 |
-
36865,
|
| 247 |
-
42863,
|
| 248 |
-
47425,
|
| 249 |
-
49870,
|
| 250 |
-
50254,
|
| 251 |
-
50258,
|
| 252 |
-
50358,
|
| 253 |
-
50359,
|
| 254 |
-
50360,
|
| 255 |
-
50361,
|
| 256 |
-
50362
|
| 257 |
-
],
|
| 258 |
-
"task_to_id": {
|
| 259 |
-
"transcribe": 50359,
|
| 260 |
-
"translate": 50358
|
| 261 |
-
},
|
| 262 |
-
"transformers_version": "4.37.0.dev0"
|
| 263 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c93a3cd362c0cb93151cc45e437ae3a288c8c24b334753bb03b4adc426128e41
|
| 3 |
-
size 967056520
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:febc8d7d4be3e124ea5299506e817b4c8da41ac3e52eccab71c0bb007a7eb9e0
|
| 3 |
-
size 1229013562
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/preprocessor_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chunk_length": 30,
|
| 3 |
-
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
-
"feature_size": 80,
|
| 5 |
-
"hop_length": 160,
|
| 6 |
-
"n_fft": 400,
|
| 7 |
-
"n_samples": 480000,
|
| 8 |
-
"nb_max_frames": 3000,
|
| 9 |
-
"padding_side": "right",
|
| 10 |
-
"padding_value": 0.0,
|
| 11 |
-
"processor_class": "WhisperProcessor",
|
| 12 |
-
"return_attention_mask": false,
|
| 13 |
-
"sampling_rate": 16000
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:844c8f18d12a6263080574d53e35b88d2942c2a11408b2ce26211e70fb757d70
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:91669aa4978f8bf563e8945a66612c1e868486915184c65fe0027e7ff2faed7f
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/trainer_state.json
DELETED
|
@@ -1,45 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.04,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 200,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.02,
|
| 13 |
-
"learning_rate": 1.9600000000000002e-05,
|
| 14 |
-
"loss": 1.5719,
|
| 15 |
-
"step": 100
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.04,
|
| 19 |
-
"learning_rate": 3.960000000000001e-05,
|
| 20 |
-
"loss": 0.3718,
|
| 21 |
-
"step": 200
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.04,
|
| 25 |
-
"eval_combined_wer": 0.2494092627599244,
|
| 26 |
-
"eval_f1_score": 0.47610377787892577,
|
| 27 |
-
"eval_label_f1": 0.650887573964497,
|
| 28 |
-
"eval_loss": 0.33680397272109985,
|
| 29 |
-
"eval_runtime": 257.5151,
|
| 30 |
-
"eval_samples_per_second": 3.883,
|
| 31 |
-
"eval_steps_per_second": 0.485,
|
| 32 |
-
"eval_wer": 0.17393154128795205,
|
| 33 |
-
"step": 200
|
| 34 |
-
}
|
| 35 |
-
],
|
| 36 |
-
"logging_steps": 100,
|
| 37 |
-
"max_steps": 5000,
|
| 38 |
-
"num_input_tokens_seen": 0,
|
| 39 |
-
"num_train_epochs": 9223372036854775807,
|
| 40 |
-
"save_steps": 200,
|
| 41 |
-
"total_flos": 7.387786248192e+18,
|
| 42 |
-
"train_batch_size": 64,
|
| 43 |
-
"trial_name": null,
|
| 44 |
-
"trial_params": null
|
| 45 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d3425d96b703d92a5e0fb65be69b99b8980fe96c840e0a4eded839951a2f5c04
|
| 3 |
-
size 4984
|
|
|
|
|
|
|
|
|
|
|
|