|
--- |
|
language: |
|
- mn |
|
thumbnail: null |
|
pipeline_tag: automatic-speech-recognition |
|
tags: |
|
- whisper |
|
- pytorch |
|
- speechbrain |
|
- Transformer |
|
- hf-asr-leaderboard |
|
license: apache-2.0 |
|
datasets: |
|
- commonvoice |
|
metrics: |
|
- wer |
|
- cer |
|
model-index: |
|
- name: asr-whisper-large-v2-commonvoice-mn |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: CommonVoice 10.0 (Mongolian) |
|
type: mozilla-foundation/common_voice_10_0 |
|
config: mn |
|
split: test |
|
args: |
|
language: mn |
|
metrics: |
|
- name: Test WER |
|
type: wer |
|
value: '64.92' |
|
inference: false |
|
--- |
|
|
|
<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe> |
|
<br/><br/> |
|
|
|
# whisper large-v2 fine-tuned on CommonVoice Mongolian |
|
|
|
This repository provides all the necessary tools to perform automatic speech |
|
recognition from an end-to-end whisper model fine-tuned on CommonVoice (Mongolian Language) within |
|
SpeechBrain. For a better experience, we encourage you to learn more about |
|
[SpeechBrain](https://speechbrain.github.io). |
|
|
|
The performance of the model is the following: |
|
|
|
| Release | Test CER | Test WER | GPUs | |
|
|:-------------:|:--------------:|:--------------:| :--------:| |
|
| 01-02-23 | 25.73 | 64.92 | 1xV100 16GB | |
|
|
|
## Pipeline description |
|
|
|
This ASR system is composed of whisper encoder-decoder blocks: |
|
- The pretrained whisper-large-v2 encoder is frozen. |
|
- The pretrained Whisper tokenizer is used. |
|
- A pretrained Whisper-large-v2 decoder ([openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)) is finetuned on CommonVoice MN. |
|
The obtained final acoustic representation is given to the greedy decoder. |
|
|
|
The system is trained with recordings sampled at 16kHz (single channel). |
|
The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed. |
|
|
|
## Install SpeechBrain |
|
|
|
First of all, please install tranformers and SpeechBrain with the following command: |
|
|
|
``` |
|
pip install speechbrain transformers==4.26.0 |
|
``` |
|
|
|
Please notice that we encourage you to read our tutorials and learn more about |
|
[SpeechBrain](https://speechbrain.github.io). |
|
|
|
### Transcribing your own audio files (in Mongolian) |
|
|
|
```python |
|
|
|
from speechbrain.inference.ASR import WhisperASR |
|
|
|
asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-large-v2-commonvoice-mn", savedir="pretrained_models/asr-whisper-large-v2-commonvoice-mn") |
|
asr_model.transcribe_file("speechbrain/asr-whisper-large-v2-commonvoice-mn/example-mn.wav") |
|
|
|
|
|
``` |
|
### Inference on GPU |
|
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method. |
|
|
|
### Training |
|
The model was trained with SpeechBrain. |
|
To train it from scratch follow these steps: |
|
1. Clone SpeechBrain: |
|
```bash |
|
git clone https://github.com/speechbrain/speechbrain/ |
|
``` |
|
2. Install it: |
|
```bash |
|
cd speechbrain |
|
pip install -r requirements.txt |
|
pip install -e . |
|
``` |
|
|
|
3. Run Training: |
|
```bash |
|
cd recipes/CommonVoice/ASR/transformer/ |
|
python train_with_whisper.py hparams/train_mn_hf_whisper.yaml --data_folder=your_data_folder |
|
``` |
|
|
|
You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/10E2xclgNx_6BFxNmv9i1HorBNnsMveP_?usp=share_link). |
|
|
|
### Limitations |
|
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets. |
|
|
|
#### Referencing SpeechBrain |
|
|
|
``` |
|
@misc{SB2021, |
|
author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua }, |
|
title = {SpeechBrain}, |
|
year = {2021}, |
|
publisher = {GitHub}, |
|
journal = {GitHub repository}, |
|
howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}}, |
|
} |
|
``` |
|
|
|
#### About SpeechBrain |
|
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains. |
|
|
|
Website: https://speechbrain.github.io/ |
|
|
|
GitHub: https://github.com/speechbrain/speechbrain |
|
|
