init

README.md

@@ -1,3 +1,103 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: openai/whisper-large-v2
+tags:
+- audio
+- automatic-speech-recognition
+- translate
+- generated_from_trainer
+language:
+- zh
+metrics:
+- cer
+- wer
+model-index:
+- name: whisper-large-v2-translate-zh-v0.1-lt-ct2
+  results: []
+---
+
+# whisper-large-v2-translate-zh-v0.1-lt-ct2
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2).
+
+## Model description
+
+3500小时 (日语音频,中文字幕) 数据微调, 翻译模式直出中文  
+
+CTranslate2 版
+
+## Usage
+
+task='translate', language='ja'  
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 4000
+- dropout: 0.1
+- mask_time_prob: 0.05
+- mask_feature_prob: 0.2
+- condition_on_previous_text_rate: 0.5
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Cer    | Wer    |
+|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
+| 1.743         | 0.0740 | 1000  | 1.5631          | 0.8223 | 1.4517 |
+| 1.6014        | 0.1479 | 2000  | 1.4808          | 0.6775 | 1.0950 |
+| 1.5549        | 0.2219 | 3000  | 1.4381          | 0.6756 | 1.1158 |
+| 1.5283        | 0.2958 | 4000  | 1.4174          | 0.6992 | 1.1137 |
+| 1.474         | 0.3698 | 5000  | 1.3849          | 0.6570 | 1.1369 |
+| 1.4193        | 0.4437 | 6000  | 1.3657          | 0.6544 | 1.1339 |
+| 1.4148        | 0.5177 | 7000  | 1.3477          | 0.6386 | 1.1647 |
+| 1.3754        | 0.5916 | 8000  | 1.3392          | 0.6228 | 1.0461 |
+| 1.3441        | 0.6656 | 9000  | 1.3362          | 0.6196 | 1.0609 |
+| 1.3545        | 0.7395 | 10000 | 1.3176          | 0.6354 | 1.2138 |
+| 1.3498        | 0.8135 | 11000 | 1.3236          | 0.6631 | 1.2232 |
+| 1.31          | 0.8874 | 12000 | 1.3020          | 0.6199 | 1.0018 |
+| 1.3213        | 0.9614 | 13000 | 1.2966          | 0.5922 | 1.0021 |
+| 1.2375        | 1.0353 | 14000 | 1.2900          | 0.6097 | 1.0639 |
+| 1.2334        | 1.1093 | 15000 | 1.2963          | 0.6150 | 1.0920 |
+| 1.2277        | 1.1832 | 16000 | 1.2888          | 0.6077 | 1.0929 |
+| 1.2087        | 1.2572 | 17000 | 1.2779          | 0.5954 | 1.0012 |
+| 1.2131        | 1.3311 | 18000 | 1.2722          | 0.5776 | 1.0075 |
+| 1.2012        | 1.4051 | 19000 | 1.2716          | 0.5726 | 1.0211 |
+| 1.1912        | 1.4790 | 20000 | 1.2707          | 0.6007 | 1.1538 |
+| 1.2127        | 1.5530 | 21000 | 1.2749          | 0.6086 | 1.0742 |
+| 1.1789        | 1.6269 | 22000 | 1.2797          | 0.5765 | 1.0072 |
+| 1.1527        | 1.7009 | 23000 | 1.2761          | 0.5855 | 1.0588 |
+| 1.1693        | 1.7748 | 24000 | 1.2701          | 0.5635 | 0.9928 |
+| 1.1709        | 1.8488 | 25000 | 1.2662          | 0.5980 | 1.0697 |
+| 1.1637        | 1.9227 | 26000 | 1.2749          | 0.5872 | 1.0392 |
+| 1.1562        | 1.9967 | 27000 | 1.2587          | 0.5651 | 1.0121 |
+| 1.0929        | 2.0706 | 28000 | 1.2668          | 0.5857 | 1.0139 |
+| 1.1232        | 2.1446 | 29000 | 1.2710          | 0.5742 | 0.9997 |
+| 1.1045        | 2.2185 | 30000 | 1.2656          | 0.5643 | 0.9897 |
+| 1.0841        | 2.2925 | 31000 | 1.2695          | 0.5835 | 1.0181 |
+| 1.0868        | 2.3664 | 32000 | 1.2707          | 0.5673 | 0.9964 |
+| 1.0938        | 2.4404 | 33000 | 1.2644          | 0.5712 | 0.9928 |
+| 1.0938        | 2.5143 | 34000 | 1.2662          | 0.5750 | 1.0109 |
+| 1.0848        | 2.5883 | 35000 | 1.2677          | 0.5841 | 1.0832 |
+| 1.0914        | 2.6622 | 36000 | 1.2638          | 0.5801 | 1.0299 |
+| 1.0688        | 2.7362 | 37000 | 1.2587          | 0.5694 | 1.0072 |
+| 1.0856        | 2.8101 | 38000 | 1.2581          | 0.5646 | 1.0057 |
+| 1.1037        | 2.8841 | 39000 | 1.2557          | 0.5771 | 1.0262 |
+| 1.0652        | 2.9580 | 40000 | 1.2566          | 0.5634 | 0.9979 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,291 @@
+{
+  "alignment_heads": [
+    [
+      10,
+      12
+    ],
+    [
+      13,
+      17
+    ],
+    [
+      16,
+      11
+    ],
+    [
+      16,
+      12
+    ],
+    [
+      16,
+      13
+    ],
+    [
+      17,
+      15
+    ],
+    [
+      17,
+      16
+    ],
+    [
+      18,
+      4
+    ],
+    [
+      18,
+      11
+    ],
+    [
+      18,
+      19
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      2
+    ],
+    [
+      21,
+      3
+    ],
+    [
+      22,
+      3
+    ],
+    [
+      22,
+      9
+    ],
+    [
+      22,
+      12
+    ],
+    [
+      23,
+      5
+    ],
+    [
+      23,
+      7
+    ],
+    [
+      23,
+      13
+    ],
+    [
+      25,
+      5
+    ],
+    [
+      26,
+      1
+    ],
+    [
+      26,
+      12
+    ],
+    [
+      27,
+      15
+    ]
+  ],
+  "lang_ids": [
+    50259,
+    50260,
+    50261,
+    50262,
+    50263,
+    50264,
+    50265,
+    50266,
+    50267,
+    50268,
+    50269,
+    50270,
+    50271,
+    50272,
+    50273,
+    50274,
+    50275,
+    50276,
+    50277,
+    50278,
+    50279,
+    50280,
+    50281,
+    50282,
+    50283,
+    50284,
+    50285,
+    50286,
+    50287,
+    50288,
+    50289,
+    50290,
+    50291,
+    50292,
+    50293,
+    50294,
+    50295,
+    50296,
+    50297,
+    50298,
+    50299,
+    50300,
+    50301,
+    50302,
+    50303,
+    50304,
+    50305,
+    50306,
+    50307,
+    50308,
+    50309,
+    50310,
+    50311,
+    50312,
+    50313,
+    50314,
+    50315,
+    50316,
+    50317,
+    50318,
+    50319,
+    50320,
+    50321,
+    50322,
+    50323,
+    50324,
+    50325,
+    50326,
+    50327,
+    50328,
+    50329,
+    50330,
+    50331,
+    50332,
+    50333,
+    50334,
+    50335,
+    50336,
+    50337,
+    50338,
+    50339,
+    50340,
+    50341,
+    50342,
+    50343,
+    50344,
+    50345,
+    50346,
+    50347,
+    50348,
+    50349,
+    50350,
+    50351,
+    50352,
+    50353,
+    50354,
+    50355,
+    50356,
+    50357
+  ],
+  "suppress_ids": [
+    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
+  ],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2868edaad88c79bae0bbb228ae2a0a19e4b5cc820d430e42e5c84f80478c63
+size 3086913076

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
+}