Downloads · 30 days
15
4% of all-time downloads
whisper-small-ru-pruned
waveletdeboshir/whisper-small-ru-pruned
whisper-small-ru-pruned is a automatic speech recognition model from waveletdeboshir. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This is a pruned version of openai/whisper-small model with only russian tokens left. Pruning was made without any fine-tuning. Method from this post was used.
All-time downloads
425
Public
Parameters
208M
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors834 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 13, 2024
- Updated
- Sep 2, 2024
- SHA
- 01116411
Model card
From the Hugging Face model README
Whisper-small-ru-pruned
Model info
This is a pruned version of openai/whisper-small model with only russian tokens left. Pruning was made without any fine-tuning. Method from this post was used.
Size
Only 10% tokens was left including special whisper tokens (no language tokens except <|ru|> and <|en|>, no timestamp tokens), 200 most popular tokens from tokenizer and 4000 most popular Russian tokens computed by tokenization of russian text corpus.
Model size is 15% less then original whisper-small:
| openai/whisper-small | waveletdeboshir/whisper-small-ru-pruned | |
|---|---|---|
| n of parameters | 242 M | 205 M |
| n of parameters (with proj_out layer) | 281 M | 208 M |
| model file size | 967 Mb | 834 Mb |
| vocab_size | 51865 | 4207 |
Usage
Model can be used as an original whisper:
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> import torchaudio
>>> # load audio
>>> wav, sr = torchaudio.load("audio.wav")
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("waveletdeboshir/whisper-small-ru-pruned")
>>> model = WhisperForConditionalGeneration.from_pretrained("waveletdeboshir/whisper-small-ru-pruned")
>>> input_features = processor(wav[0], sampling_rate=sr, return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
['<|startoftranscript|><|ru|><|transcribe|><|notimestamps|> Начинаем работу.<|endoftext|>']
The context tokens can be removed from the start of the transcription by setting skip_special_tokens=True.
Other pruned whisper models
Metrics
| metric | dataset | openai/whisper-small | waveletdeboshir/whisper-small-ru-pruned |
|---|---|---|---|
| WER* | golos-test-crowd | 0.3358 | 0.3471 |
| CER* | golos-test-crowd | 0.1561 | 0.1444 |
| WER* | common_voice_15_0_test | 0.1749 | 0.1748 |
| WER | common_voice_15_0_test | 0.2492 | 0.2498 |
| *Metrics were computed after text normalization |
You can fine-tune this model on your data to achive better performance.
Colab for vocab pruning
Check https://github.com/waveletdeboshir/whisper-lang-remover
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ru
- Created
- Aug 13, 2024
- Updated
- Sep 2, 2024