byoussef/whisper-large-v2-Ko
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: byoussef/whisper-large-v2-Ko
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-20 23:21:52 +08:00
commit d3f9b3adfa
29 changed files with 155167 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

1
.gitignore vendored Normal file
View File

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

105
README.md Normal file
View File

@@ -0,0 +1,105 @@
---
language:
- ko
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- Bingsu/zeroth-korean
metrics:
- wer
pipeline_tag: automatic-speech-recognition
base_model: openai/whisper-large-v2
model-index:
- name: whisper-large-v2-Ko
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Bingsu/zeroth-korean
type: Bingsu/zeroth-korean
metrics:
- type: wer
value: 2.9
name: Wer
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: google/fleurs
type: google/fleurs
config: ko_kr
split: test
metrics:
- type: wer
value: 20.66
name: WER
---
<!-- 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-large-v2-Ko
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0617
- Wer: **2.9**
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
***** train metrics *****
epoch = 50.0
train_loss = 0.0234
train_runtime = 16:20:18.00
train_samples = 22262
train_samples_per_second = 19.042
train_steps_per_second = 0.085
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 7
- total_train_batch_size: 224
- total_eval_batch_size: 112
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0299 | 10.0 | 1000 | 0.0745 | 0.0447 |
| 0.0085 | 20.0 | 2000 | 0.0608 | 0.0353 |
| 0.0036 | 30.0 | 3000 | 0.0593 | 0.0302 |
| 0.0013 | 40.0 | 4000 | 0.0609 | 0.0282 |
| 0.0008 | 50.0 | 5000 | 0.0617 | 0.0290 |
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.10.1
- Tokenizers 0.13.2

108
added_tokens.json Normal file
View File

@@ -0,0 +1,108 @@
{
"<|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,
"<|nocaptions|>": 50362,
"<|notimestamps|>": 50363,
"<|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,
"<|startoflm|>": 50360,
"<|startofprev|>": 50361,
"<|startoftranscript|>": 50258,
"<|su|>": 50357,
"<|sv|>": 50273,
"<|sw|>": 50318,
"<|ta|>": 50287,
"<|te|>": 50299,
"<|tg|>": 50331,
"<|th|>": 50289,
"<|tk|>": 50341,
"<|tl|>": 50348,
"<|transcribe|>": 50359,
"<|translate|>": 50358,
"<|tr|>": 50268,
"<|tt|>": 50351,
"<|uk|>": 50280,
"<|ur|>": 50290,
"<|uz|>": 50337,
"<|vi|>": 50278,
"<|yi|>": 50335,
"<|yo|>": 50325,
"<|zh|>": 50260
}

14
all_results.json Normal file
View File

@@ -0,0 +1,14 @@
{
"epoch": 50.0,
"eval_loss": 0.05855414643883705,
"eval_runtime": 44.2001,
"eval_samples": 456,
"eval_samples_per_second": 10.317,
"eval_steps_per_second": 0.113,
"eval_wer": 0.027031108426457263,
"train_loss": 0.023422172606736423,
"train_runtime": 58818.0035,
"train_samples": 22262,
"train_samples_per_second": 19.042,
"train_steps_per_second": 0.085
}

50
config.json Normal file
View File

@@ -0,0 +1,50 @@
{
"_name_or_path": "openai/whisper-large-v2",
"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": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"forced_decoder_ids": null,
"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,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 80,
"pad_token_id": 50257,
"scale_embedding": false,
"torch_dtype": "float32",
"transformers_version": "4.27.0.dev0",
"use_cache": true,
"use_weighted_layer_sum": false,
"vocab_size": 51865
}

9
eval_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 50.0,
"eval_loss": 0.05855414643883705,
"eval_runtime": 44.2001,
"eval_samples": 456,
"eval_samples_per_second": 10.317,
"eval_steps_per_second": 0.113,
"eval_wer": 0.027031108426457263
}

223
generation_config.json Normal file
View File

@@ -0,0 +1,223 @@
{
"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
],
[
3,
50363
]
],
"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": 1,
"max_length": 448,
"no_timestamps_token_id": 50363,
"pad_token_id": 50256,
"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,
50360,
50361,
50362
],
"task_to_id": {
"transcribe": 50359,
"translate": 50358
},
"transformers_version": "4.27.0.dev0"
}

50000
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d5cd1af64586a6ae490a1d3750ab1f81696cca989ab3f95b59684708f87a011
size 6173370152

1742
normalizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

14
preprocessor_config.json Normal file
View File

@@ -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
}

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4a776d0523426a509c452090fefc1963e4b3fe4f2142d23dec4dcb9412c8fd1
size 6173647530

3
runs/Mar10_16-11-07_dgx01/1678432311.2770696/events.out.tfevents.1678432311.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bda002730f42a5cbc386289c0db41e906c952cef598fb43593588fe4457910ab
size 5752

3
runs/Mar10_16-11-07_dgx01/events.out.tfevents.1678432311.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ecd27e9383c44a051db1905ae0ec1c534aa5ea965db950b123374dfd6d4d36f7
size 4681

3
runs/Mar10_16-50-10_dgx01/1678434654.2291248/events.out.tfevents.1678434654.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0c5ebc2134d8112336ff0502d6d928e12925bba89abf1f90bb73cf31ed862b7
size 5752

3
runs/Mar10_16-50-10_dgx01/events.out.tfevents.1678434654.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fc94d3c7d6fc91941c06220efb21b95676906823f6f7bf0d67529322e219771
size 4681

3
runs/Mar10_17-19-34_dgx01/1678436421.6493232/events.out.tfevents.1678436421.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddab4c7e0a789c4ddbc0fe8f7d76bf1f5d9d2206b62f613cfb3f1fb1d79d6884
size 5752

3
runs/Mar10_17-19-34_dgx01/events.out.tfevents.1678436421.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8dc6db71835deb6acb97f835fd82262f3099682cc94d182ef4ddeb3326dc0d4b
size 5451

3
runs/Mar10_17-33-14_dgx01/1678437237.5728078/events.out.tfevents.1678437237.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a557bdcf2dd05c37f5a9e22a5a4d805cb59ecd55f9ea1128b558dc1f3c56ff8
size 5752

3
runs/Mar10_17-33-14_dgx01/events.out.tfevents.1678437237.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:434bf45b41b18344619ea0208b4d1edf6588b017db78a9953bd3cb75581e96d5
size 38010

3
runs/Mar10_17-33-14_dgx01/events.out.tfevents.1678496566.dgx01 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65ac3601b887eb45027178085dabdd61f9facf9902f9f93a06c4373b3814352c
size 40

133
special_tokens_map.json Normal file
View File

@@ -0,0 +1,133 @@
{
"additional_special_tokens": [
"<|endoftext|>",
"<|startoftranscript|>",
"<|en|>",
"<|zh|>",
"<|de|>",
"<|es|>",
"<|ru|>",
"<|ko|>",
"<|fr|>",
"<|ja|>",
"<|pt|>",
"<|tr|>",
"<|pl|>",
"<|ca|>",
"<|nl|>",
"<|ar|>",
"<|sv|>",
"<|it|>",
"<|id|>",
"<|hi|>",
"<|fi|>",
"<|vi|>",
"<|he|>",
"<|uk|>",
"<|el|>",
"<|ms|>",
"<|cs|>",
"<|ro|>",
"<|da|>",
"<|hu|>",
"<|ta|>",
"<|no|>",
"<|th|>",
"<|ur|>",
"<|hr|>",
"<|bg|>",
"<|lt|>",
"<|la|>",
"<|mi|>",
"<|ml|>",
"<|cy|>",
"<|sk|>",
"<|te|>",
"<|fa|>",
"<|lv|>",
"<|bn|>",
"<|sr|>",
"<|az|>",
"<|sl|>",
"<|kn|>",
"<|et|>",
"<|mk|>",
"<|br|>",
"<|eu|>",
"<|is|>",
"<|hy|>",
"<|ne|>",
"<|mn|>",
"<|bs|>",
"<|kk|>",
"<|sq|>",
"<|sw|>",
"<|gl|>",
"<|mr|>",
"<|pa|>",
"<|si|>",
"<|km|>",
"<|sn|>",
"<|yo|>",
"<|so|>",
"<|af|>",
"<|oc|>",
"<|ka|>",
"<|be|>",
"<|tg|>",
"<|sd|>",
"<|gu|>",
"<|am|>",
"<|yi|>",
"<|lo|>",
"<|uz|>",
"<|fo|>",
"<|ht|>",
"<|ps|>",
"<|tk|>",
"<|nn|>",
"<|mt|>",
"<|sa|>",
"<|lb|>",
"<|my|>",
"<|bo|>",
"<|tl|>",
"<|mg|>",
"<|as|>",
"<|tt|>",
"<|haw|>",
"<|ln|>",
"<|ha|>",
"<|ba|>",
"<|jw|>",
"<|su|>",
"<|translate|>",
"<|transcribe|>",
"<|startoflm|>",
"<|startofprev|>",
"<|nocaptions|>",
"<|notimestamps|>"
],
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

101384
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"special_tokens_map_file": null,
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 50.0,
"train_loss": 0.023422172606736423,
"train_runtime": 58818.0035,
"train_samples": 22262,
"train_samples_per_second": 19.042,
"train_steps_per_second": 0.085
}

1270
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6370c9bd72ca7d02215d3b690a80d06edb2b90d8f1d5656d1262b070e8a7b2fb
size 3695

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long