初始化项目，由ModelHub XC社区提供模型
Model: antony66/whisper-large-v3-russian Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
*.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
|
||||
86
README.md
Normal file
86
README.md
Normal file
@@ -0,0 +1,86 @@
|
||||
---
|
||||
language:
|
||||
- ru
|
||||
library_name: transformers
|
||||
tags:
|
||||
- asr
|
||||
- whisper
|
||||
- russian
|
||||
datasets:
|
||||
- mozilla-foundation/common_voice_17_0
|
||||
metrics:
|
||||
- wer
|
||||
---
|
||||
|
||||
# Model Details
|
||||
|
||||
This is a version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) finetuned for better support of Russian language.
|
||||
|
||||
Dataset used for finetuning is Common Voice 17.0, Russian part, that contains over 200k rows.
|
||||
|
||||
After preprocessing of the original dataset (all splits were mixed and splited to a new train + test split by 0.95/0.05,
|
||||
that is 225761/11883 rows respectively) the original Whisper v3 has WER 9.84 while the finetuned version shows 6.39 (so far).
|
||||
|
||||
The finetuning process took over 60 hours on dual Tesla A100 80Gb.
|
||||
|
||||
## Usage
|
||||
|
||||
In order to process phone calls it is highly recommended that you preprocess your records and adjust volume before performing ASR. For example, like this:
|
||||
|
||||
```bash
|
||||
sox record.wav -r 16k record-normalized.wav norm -0.5 compand 0.3,1 -90,-90,-70,-70,-60,-20,0,0 -5 0 0.2
|
||||
```
|
||||
|
||||
Then your ASR code should look somewhat like this:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import WhisperForConditionalGeneration, WhisperProcessor, pipeline
|
||||
|
||||
torch_dtype = torch.bfloat16 # set your preferred type here
|
||||
|
||||
device = 'cpu'
|
||||
if torch.cuda.is_available():
|
||||
device = 'cuda'
|
||||
elif torch.backends.mps.is_available():
|
||||
device = 'mps'
|
||||
setattr(torch.distributed, "is_initialized", lambda : False) # monkey patching
|
||||
device = torch.device(device)
|
||||
|
||||
whisper = WhisperForConditionalGeneration.from_pretrained(
|
||||
"antony66/whisper-large-v3-russian", torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True,
|
||||
# add attn_implementation="flash_attention_2" if your GPU supports it
|
||||
)
|
||||
|
||||
processor = WhisperProcessor.from_pretrained("antony66/whisper-large-v3-russian")
|
||||
|
||||
asr_pipeline = pipeline(
|
||||
"automatic-speech-recognition",
|
||||
model=whisper,
|
||||
tokenizer=processor.tokenizer,
|
||||
feature_extractor=processor.feature_extractor,
|
||||
max_new_tokens=256,
|
||||
chunk_length_s=30,
|
||||
batch_size=16,
|
||||
return_timestamps=True,
|
||||
torch_dtype=torch_dtype,
|
||||
device=device,
|
||||
)
|
||||
|
||||
# read your wav file into variable wav. For example:
|
||||
from io import BufferIO
|
||||
wav = BytesIO()
|
||||
with open('record-normalized.wav', 'rb') as f:
|
||||
wav.write(f.read())
|
||||
wav.seek(0)
|
||||
|
||||
# get the transcription
|
||||
asr = asr_pipeline(wav, generate_kwargs={"language": "russian", "max_new_tokens": 256}, return_timestamps=False)
|
||||
|
||||
print(asr['text'])
|
||||
|
||||
```
|
||||
|
||||
## Work in progress
|
||||
|
||||
This model is in WIP state for now. The goal is to finetune it for speech recognition of phone calls as much as possible. If you want to contribute and you know or have any good dataset please let me know. Your help will be much appreciated.
|
||||
1611
added_tokens.json
Normal file
1611
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
50
config.json
Normal file
50
config.json
Normal file
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"_name_or_path": "openai/whisper-large-v3",
|
||||
"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,
|
||||
"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,
|
||||
"median_filter_width": 7,
|
||||
"model_type": "whisper",
|
||||
"num_hidden_layers": 32,
|
||||
"num_mel_bins": 128,
|
||||
"pad_token_id": 50256,
|
||||
"scale_embedding": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.2",
|
||||
"use_cache": true,
|
||||
"use_weighted_layer_sum": false,
|
||||
"vocab_size": 51866
|
||||
}
|
||||
258
generation_config.json
Normal file
258
generation_config.json
Normal file
@@ -0,0 +1,258 @@
|
||||
{
|
||||
"alignment_heads": [
|
||||
[
|
||||
7,
|
||||
0
|
||||
],
|
||||
[
|
||||
10,
|
||||
17
|
||||
],
|
||||
[
|
||||
12,
|
||||
18
|
||||
],
|
||||
[
|
||||
13,
|
||||
12
|
||||
],
|
||||
[
|
||||
16,
|
||||
1
|
||||
],
|
||||
[
|
||||
17,
|
||||
14
|
||||
],
|
||||
[
|
||||
19,
|
||||
11
|
||||
],
|
||||
[
|
||||
21,
|
||||
4
|
||||
],
|
||||
[
|
||||
24,
|
||||
1
|
||||
],
|
||||
[
|
||||
25,
|
||||
6
|
||||
]
|
||||
],
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"begin_suppress_tokens": [
|
||||
220,
|
||||
50257
|
||||
],
|
||||
"bos_token_id": 50257,
|
||||
"decoder_start_token_id": 50258,
|
||||
"eos_token_id": 50257,
|
||||
"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,
|
||||
"<|yue|>": 50358,
|
||||
"<|zh|>": 50260
|
||||
},
|
||||
"language": "russian",
|
||||
"max_initial_timestamp_index": 50,
|
||||
"max_length": 448,
|
||||
"no_timestamps_token_id": 50364,
|
||||
"pad_token_id": 50257,
|
||||
"prev_sot_token_id": 50362,
|
||||
"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,
|
||||
50359,
|
||||
50360,
|
||||
50361,
|
||||
50362,
|
||||
50363
|
||||
],
|
||||
"task": "transcribe",
|
||||
"task_to_id": {
|
||||
"transcribe": 50360,
|
||||
"translate": 50359
|
||||
},
|
||||
"transformers_version": "4.40.2"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8eca426464823c28293a4d68be605020c6c3dca8050d5b4e4b4c8118c561382e
|
||||
size 3087132232
|
||||
1742
normalizer.json
Normal file
1742
normalizer.json
Normal file
File diff suppressed because it is too large
Load Diff
14
preprocessor_config.json
Normal file
14
preprocessor_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"chunk_length": 30,
|
||||
"feature_extractor_type": "WhisperFeatureExtractor",
|
||||
"feature_size": 128,
|
||||
"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
|
||||
}
|
||||
139
special_tokens_map.json
Normal file
139
special_tokens_map.json
Normal file
@@ -0,0 +1,139 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|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|>",
|
||||
"<|yue|>",
|
||||
"<|translate|>",
|
||||
"<|transcribe|>",
|
||||
"<|startoflm|>",
|
||||
"<|startofprev|>",
|
||||
"<|nospeech|>",
|
||||
"<|notimestamps|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
12996
tokenizer_config.json
Normal file
12996
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
50259
vocab.json
Normal file
50259
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user