biodatlab/whisper-th-large-combined
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: biodatlab/whisper-th-large-combined
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-15 09:13:11 +08:00
commit f93f97184f
25 changed files with 120299 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

6
.gitignore vendored Normal file
View File

@@ -0,0 +1,6 @@
checkpoint-*
data
*.zip
*.sh
*.py
*.csv

79
README.md Normal file
View File

@@ -0,0 +1,79 @@
---
datasets:
- mozilla-foundation/common_voice_11_0
language:
- th
license: apache-2.0
metrics:
- wer
tags:
- whisper-event
- generated_from_trainer
model-index:
- name: Whisper Large Thai Combined - 1000iter
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_11_0 th
type: mozilla-foundation/common_voice_11_0
config: th
split: test
args: th
metrics:
- type: wer
value: 15.510316437482013
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 Thai Combined - 1000iter
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the mozilla-foundation/common_voice_11_0 th dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1244
- Wer: 15.5103
## 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: 100
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.1845 | 1.05 | 5000 | 0.1244 | 15.5103 |
### Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2

109
added_tokens.json Normal file
View File

@@ -0,0 +1,109 @@
{
"<|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,
"<|endoftext|>": 50257,
"<|en|>": 50259,
"<|es|>": 50262,
"<|et|>": 50307,
"<|eu|>": 50310,
"<|fa|>": 50300,
"<|fi|>": 50277,
"<|fo|>": 50338,
"<|fr|>": 50265,
"<|gl|>": 50319,
"<|gu|>": 50333,
"<|haw|>": 50352,
"<|ha|>": 50354,
"<|hi|>": 50276,
"<|hr|>": 50291,
"<|ht|>": 50339,
"<|hu|>": 50286,
"<|hy|>": 50312,
"<|id|>": 50275,
"<|is|>": 50311,
"<|it|>": 50274,
"<|iw|>": 50279,
"<|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
}

12
all_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"epoch": 1.05,
"eval_loss": 0.12443096935749054,
"eval_runtime": 3970.0341,
"eval_samples_per_second": 2.753,
"eval_steps_per_second": 0.344,
"eval_wer": 15.510316437482013,
"train_loss": 0.27737956771850586,
"train_runtime": 13393.8488,
"train_samples_per_second": 5.973,
"train_steps_per_second": 0.373
}

41
config.json Normal file
View File

@@ -0,0 +1,41 @@
{
"_name_or_path": "openai/whisper-large-v2",
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"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,
"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": "4.26.0.dev0",
"use_cache": true,
"vocab_size": 51865
}

8
eval_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.05,
"eval_loss": 0.12443096935749054,
"eval_runtime": 3970.0341,
"eval_samples_per_second": 2.753,
"eval_steps_per_second": 0.344,
"eval_wer": 15.510316437482013
}

316
generation_config.json Normal file
View File

@@ -0,0 +1,316 @@
{
"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
]
],
"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": "4.44.2"
}

50000
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1742
normalizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

16256
preprocessor_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1e0b5b4c9a89d7d60fb795448c3102e07af87fa73c5fce7c0206c6bd99a7e7b
size 6173655480

3
runs/Dec12_15-58-16_rtx-i7/1670842527.5495274/events.out.tfevents.1670842527.rtx-i7.926518.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1f9a3763258278670670d4f5dde34da04e1d86fd2b62f5c49ddaed65bff6591
size 5707

3
runs/Dec12_15-58-16_rtx-i7/events.out.tfevents.1670842527.rtx-i7.926518.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85ea3aac550e16990688d3ef973b0ad1072c107c69e3f0dec18c0f983dd03315
size 4180

3
runs/Dec12_18-24-41_rtx-i7/1670844581.7416902/events.out.tfevents.1670844581.rtx-i7.2515182.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22b899aa7bfb4bfe4f420c8efdcd726f0f9fad5f8b56565c8fc0c1250153f163
size 5707

3
runs/Dec12_18-24-41_rtx-i7/events.out.tfevents.1670844581.rtx-i7.2515182.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:106476efc830749b92f5c6e5d39eec7672cd4ca12b7691f07c688f804caf9ad6
size 4180

3
runs/Dec12_18-32-11_rtx-i7/1670844777.939483/events.out.tfevents.1670844777.rtx-i7.2748267.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74a7e6b291cb0d3820757f0dd5b088e64e7c0f839d086287e90ede1b8e905065
size 5707

3
runs/Dec12_18-32-11_rtx-i7/events.out.tfevents.1670844777.rtx-i7.2748267.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4b620f874de78ca120a4431697832d0a545db159ea5ab292746e0393e1b88ae
size 36237

3
runs/Dec12_18-32-11_rtx-i7/events.out.tfevents.1670862145.rtx-i7.2748267.2 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:653ea0450ed518d42812f5bff2416a78820da28ef94a6d8dffaf92d6d2f70291
size 358

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|>",
"<|iw|>",
"<|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": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

36
tokenizer_config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"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,
"name_or_path": "openai/whisper-large-v2",
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"special_tokens_map_file": null,
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

7
train_results.json Normal file
View File

@@ -0,0 +1,7 @@
{
"epoch": 1.05,
"train_loss": 0.27737956771850586,
"train_runtime": 13393.8488,
"train_samples_per_second": 5.973,
"train_steps_per_second": 0.373
}

1234
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:cf3381b0bf533e9b315d9c455f78178b32759366a0ab4b88e60f402dbfb82bf9
size 3515

50259
vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff