whisper-medium-sb-lug-eng

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: openai/whisper-medium
+tags:
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: whisper-medium-sb-lug-eng
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-medium-sb-lug-eng
+
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1179
+- Wer Lug: 0.558
+- Wer Eng: 0.025
+- Wer Mean: 0.292
+- Cer Lug: 0.285
+- Cer Eng: 0.011
+- Cer Mean: 0.148
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 12000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer Lug | Wer Eng | Wer Mean | Cer Lug | Cer Eng | Cer Mean |
+|:-------------:|:------:|:-----:|:---------------:|:-------:|:-------:|:--------:|:-------:|:-------:|:--------:|
+| 0.7169        | 0.0417 | 500   | 0.2614          | 0.715   | 0.039   | 0.377    | 0.264   | 0.02    | 0.142    |
+| 0.5343        | 0.0833 | 1000  | 0.1939          | 0.391   | 0.029   | 0.21     | 0.147   | 0.013   | 0.08     |
+| 0.4529        | 0.125  | 1500  | 0.1864          | 0.256   | 0.032   | 0.144    | 0.069   | 0.015   | 0.042    |
+| 0.3733        | 0.1667 | 2000  | 0.1597          | 0.276   | 0.024   | 0.15     | 0.093   | 0.01    | 0.052    |
+| 0.3874        | 0.2083 | 2500  | 0.1520          | 0.733   | 0.023   | 0.378    | 0.314   | 0.01    | 0.162    |
+| 0.3641        | 0.25   | 3000  | 0.1408          | 0.762   | 0.027   | 0.395    | 0.339   | 0.012   | 0.176    |
+| 0.3682        | 0.2917 | 3500  | 0.1413          | 0.956   | 0.016   | 0.486    | 0.503   | 0.006   | 0.254    |
+| 0.3379        | 0.3333 | 4000  | 0.1376          | 0.358   | 0.027   | 0.192    | 0.177   | 0.01    | 0.094    |
+| 0.3324        | 0.375  | 4500  | 0.1317          | 0.249   | 0.022   | 0.135    | 0.107   | 0.007   | 0.057    |
+| 0.3003        | 0.4167 | 5000  | 0.1304          | 0.403   | 0.025   | 0.214    | 0.174   | 0.009   | 0.091    |
+| 0.2259        | 1.0383 | 5500  | 0.1294          | 0.608   | 0.021   | 0.314    | 0.263   | 0.007   | 0.135    |
+| 0.2259        | 1.08   | 6000  | 0.1309          | 0.835   | 0.025   | 0.43     | 0.417   | 0.008   | 0.213    |
+| 0.2531        | 1.1217 | 6500  | 0.1252          | 0.249   | 0.022   | 0.135    | 0.109   | 0.008   | 0.058    |
+| 0.2258        | 1.1633 | 7000  | 0.1259          | 0.384   | 0.023   | 0.203    | 0.178   | 0.007   | 0.093    |
+| 0.2205        | 1.205  | 7500  | 0.1264          | 0.376   | 0.021   | 0.198    | 0.181   | 0.007   | 0.094    |
+| 0.2235        | 1.2467 | 8000  | 0.1274          | 0.395   | 0.025   | 0.21     | 0.196   | 0.008   | 0.102    |
+| 0.2219        | 1.2883 | 8500  | 0.1252          | 0.349   | 0.029   | 0.189    | 0.162   | 0.01    | 0.086    |
+| 0.2334        | 1.33   | 9000  | 0.1224          | 0.292   | 0.028   | 0.16     | 0.128   | 0.01    | 0.069    |
+| 0.2339        | 1.3717 | 9500  | 0.1207          | 0.305   | 0.026   | 0.166    | 0.136   | 0.01    | 0.073    |
+| 0.2094        | 1.4133 | 10000 | 0.1194          | 0.569   | 0.023   | 0.296    | 0.276   | 0.009   | 0.143    |
+| 0.1643        | 2.035  | 10500 | 0.1184          | 0.818   | 0.026   | 0.422    | 0.466   | 0.011   | 0.239    |
+| 0.1549        | 2.0767 | 11000 | 0.1196          | 0.651   | 0.022   | 0.336    | 0.374   | 0.008   | 0.191    |
+| 0.1727        | 2.1183 | 11500 | 0.1182          | 0.547   | 0.025   | 0.286    | 0.29    | 0.011   | 0.15     |
+| 0.1617        | 2.16   | 12000 | 0.1179          | 0.558   | 0.025   | 0.292    | 0.285   | 0.011   | 0.148    |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.2.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,248 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": 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,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.42.3"
+}