akera/whisper-medium-sb-lug-eng

README.md

@@ -0,0 +1,96 @@
+---
+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: 0.1499
+- Wer Lug: 0.16
+- Wer Eng: 0.038
+- Wer Mean: 0.099
+- Cer Lug: 0.036
+- Cer Eng: 0.019
+- Cer Mean: 0.028
+
+## 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: 12
+- eval_batch_size: 4
+- 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: 3000
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:--------:|:-------:|:-------:|:--------:|
+| 2.077         | 0.0333 | 100  | 1.0935          | 1.012   | 2.041   | 1.527    | 0.332   | 1.527   | 0.929    |
+| 1.217         | 0.0667 | 200  | 0.5019          | 0.752   | 0.317   | 0.535    | 0.184   | 0.358   | 0.271    |
+| 0.9285        | 0.1    | 300  | 0.3713          | 0.545   | 0.048   | 0.296    | 0.141   | 0.03    | 0.085    |
+| 0.8392        | 0.1333 | 400  | 0.3095          | 0.465   | 0.038   | 0.251    | 0.093   | 0.019   | 0.056    |
+| 0.7857        | 0.1667 | 500  | 0.2804          | 0.413   | 0.043   | 0.228    | 0.08    | 0.022   | 0.051    |
+| 0.6783        | 0.2    | 600  | 0.2533          | 0.373   | 0.039   | 0.206    | 0.073   | 0.02    | 0.047    |
+| 0.674         | 0.2333 | 700  | 0.2404          | 0.309   | 0.036   | 0.173    | 0.062   | 0.016   | 0.039    |
+| 0.6213        | 0.2667 | 800  | 0.2323          | 0.325   | 0.034   | 0.179    | 0.066   | 0.016   | 0.041    |
+| 0.593         | 0.3    | 900  | 0.2205          | 0.275   | 0.034   | 0.154    | 0.057   | 0.017   | 0.037    |
+| 0.5423        | 0.3333 | 1000 | 0.2059          | 0.271   | 0.032   | 0.152    | 0.055   | 0.015   | 0.035    |
+| 0.5358        | 0.3667 | 1100 | 0.1959          | 0.246   | 0.029   | 0.138    | 0.051   | 0.013   | 0.032    |
+| 0.552         | 0.4    | 1200 | 0.1910          | 0.25    | 0.037   | 0.144    | 0.054   | 0.019   | 0.036    |
+| 0.5313        | 0.4333 | 1300 | 0.1786          | 0.208   | 0.027   | 0.117    | 0.045   | 0.013   | 0.029    |
+| 0.482         | 0.4667 | 1400 | 0.1788          | 0.212   | 0.036   | 0.124    | 0.045   | 0.021   | 0.033    |
+| 0.4561        | 0.5    | 1500 | 0.1692          | 0.191   | 0.026   | 0.109    | 0.041   | 0.015   | 0.028    |
+| 0.4618        | 0.5333 | 1600 | 0.1702          | 0.187   | 0.032   | 0.11     | 0.042   | 0.016   | 0.029    |
+| 0.4357        | 0.5667 | 1700 | 0.1717          | 0.187   | 0.038   | 0.112    | 0.042   | 0.019   | 0.03     |
+| 0.45          | 0.6    | 1800 | 0.1696          | 0.172   | 0.035   | 0.103    | 0.038   | 0.018   | 0.028    |
+| 0.417         | 0.6333 | 1900 | 0.1705          | 0.176   | 0.032   | 0.104    | 0.038   | 0.018   | 0.028    |
+| 0.3955        | 0.6667 | 2000 | 0.1649          | 0.165   | 0.035   | 0.1      | 0.039   | 0.018   | 0.028    |
+| 0.4066        | 0.7    | 2100 | 0.1614          | 0.162   | 0.031   | 0.097    | 0.038   | 0.015   | 0.026    |
+| 0.4482        | 0.7333 | 2200 | 0.1617          | 0.165   | 0.03    | 0.098    | 0.038   | 0.016   | 0.027    |
+| 0.4169        | 0.7667 | 2300 | 0.1613          | 0.171   | 0.029   | 0.1      | 0.039   | 0.015   | 0.027    |
+| 0.4222        | 0.8    | 2400 | 0.1582          | 0.168   | 0.029   | 0.099    | 0.038   | 0.017   | 0.028    |
+| 0.3922        | 0.8333 | 2500 | 0.1574          | 0.175   | 0.032   | 0.104    | 0.039   | 0.016   | 0.027    |
+| 0.4123        | 0.8667 | 2600 | 0.1547          | 0.165   | 0.034   | 0.099    | 0.037   | 0.016   | 0.027    |
+| 0.3771        | 0.9    | 2700 | 0.1540          | 0.169   | 0.036   | 0.102    | 0.038   | 0.017   | 0.028    |
+| 0.3923        | 0.9333 | 2800 | 0.1511          | 0.161   | 0.038   | 0.099    | 0.037   | 0.019   | 0.028    |
+| 0.3987        | 0.9667 | 2900 | 0.1501          | 0.162   | 0.038   | 0.1      | 0.036   | 0.019   | 0.027    |
+| 0.3637        | 1.0    | 3000 | 0.1499          | 0.16    | 0.038   | 0.099    | 0.036   | 0.019   | 0.028    |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- 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"
+}