|
--- |
|
language: "en" |
|
thumbnail: |
|
tags: |
|
- automatic-speech-recognition |
|
- CTC |
|
- Attention |
|
- Tranformer |
|
- pytorch |
|
- speechbrain |
|
license: "apache-2.0" |
|
datasets: |
|
- librispeech |
|
metrics: |
|
- wer |
|
- cer |
|
--- |
|
|
|
<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/> |
|
|
|
# CRDNN with CTC/Attention and RNNLM trained on LibriSpeech |
|
|
|
This repository provides all the necessary tools to perform automatic speech |
|
recognition from an end-to-end system pretrained on LibriSpeech (EN) 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 clean WER | Test other WER | GPUs | |
|
|:-------------:|:--------------:|:--------------:|:--------:| |
|
| 05-03-21 | 2.90 | 8.51 | 1xV100 16GB | |
|
|
|
## Pipeline description |
|
|
|
This ASR system is composed of 3 different but linked blocks: |
|
1. Tokenizer (unigram) that transforms words into subword units and trained with |
|
the train transcriptions of LibriSpeech. |
|
2. Neural language model (Transformer LM) trained on the full 10M words dataset. |
|
3. Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of |
|
N blocks of convolutional neural networks with normalization and pooling on the |
|
frequency domain. Then, a bidirectional LSTM with projection layers is connected |
|
to a final DNN to obtain the final acoustic representation that is given to |
|
the CTC and attention decoders. |
|
|
|
## Install SpeechBrain |
|
|
|
First of all, please install SpeechBrain with the following command: |
|
|
|
``` |
|
pip install speechbrain |
|
``` |
|
|
|
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 English) |
|
|
|
```python |
|
from speechbrain.pretrained import EncoderDecoderASR |
|
|
|
asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-transformerlm-librispeech", savedir="pretrained_models/asr-crdnn-transformerlm-librispeech") |
|
asr_model.transcribe_file("speechbrain/asr-crdnn-transformerlm-librispeech/example.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 (Commit hash: 'eca313cc'). |
|
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/LibriSpeech/ASR/seq2seq |
|
python train.py hparams/train_BPE_5000.yaml --data_folder=your_data_folder |
|
``` |
|
|
|
You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1kSwdBT8kDhnmTLzrOPDL77LX_Eq-3Tzl?usp=sharing). |
|
|
|
### Limitations |
|
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets. |
|
|
|
|
|
# **About SpeechBrain** |
|
- Website: https://speechbrain.github.io/ |
|
- Code: https://github.com/speechbrain/speechbrain/ |
|
- HuggingFace: https://huggingface.co/speechbrain/ |
|
|
|
|
|
# **Citing SpeechBrain** |
|
Please, cite SpeechBrain if you use it for your research or business. |
|
|
|
|
|
```bibtex |
|
@misc{speechbrain, |
|
title={{SpeechBrain}: A General-Purpose Speech Toolkit}, |
|
author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio}, |
|
year={2021}, |
|
eprint={2106.04624}, |
|
archivePrefix={arXiv}, |
|
primaryClass={eess.AS}, |
|
note={arXiv:2106.04624} |
|
} |
|
``` |
|
|