Asr Wav2vec2 Commonvoice 14 Es

🚀 wav2vec 2.0 with CTC trained on CommonVoice Spanish (No LM)

This repository offers all the essential tools for automatic speech recognition using an end - to - end system pretrained on CommonVoice (Spanish Language) within SpeechBrain. For a better experience, explore SpeechBrain.

✨ Features

• Model Information:
  • Language: Spanish (es)
  • Pipeline Tag: automatic - speech - recognition
  • Tags: CTC, pytorch, speechbrain, Transformer
  • License: apache - 2.0
  • Datasets: commonvoice.14.0
  • Metrics: wer, cer
• Model Performance: | Release | Test CER | Test WER | GPUs | |:-------------:|:--------------:|:--------------:| :--------:| | 15 - 08 - 23 | 3.80 | 13.28 | 1xV100 32GB |

🚀 Quick Start

📦 Installation

First, install transformers and SpeechBrain with the following command:

pip install speechbrain transformers

💡 Usage Tip

We encourage you to read our tutorials and learn more about SpeechBrain.

💻 Usage Examples

Basic Usage

Transcribing your own audio files (in Spanish):

from speechbrain.inference.ASR import EncoderASR

asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-14-es", savedir="pretrained_models/asr-wav2vec2-commonvoice-14-es")
asr_model.transcribe_file("speechbrain/asr-wav2vec2-commonvoice-14-es/example_es.wav")

Advanced Usage

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

Parallel Inference on a Batch

See this Colab notebook to learn how to transcribe in parallel a batch of input sentences using a pre - trained model.

Training

The model was trained with SpeechBrain. To train it from scratch:

1. Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

2. Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

3. Run Training:

cd recipes/CommonVoice/ASR/CTC/
python train_with_wav2vec.py hparams/train_es_with_wav2vec.yaml --data_folder=your_data_folder

You can find our training results (models, logs, etc) here.

🔧 Technical Details

Pipeline description

This ASR system consists of 2 different but linked blocks:

• Tokenizer (unigram) that transforms words into unigrams and is trained with the train transcriptions (train.tsv) of CommonVoice (es).
• Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model (wav2vec2 - large - xlsr - 53) is combined with two DNN layers and finetuned on CommonVoice DE. The obtained final acoustic representation is given to the CTC 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.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

📚 Documentation

Model Index

• Name: asr - wav2vec2 - commonvoice - 14 - es
• Results:
  • Task:
    • Name: Automatic Speech Recognition
    • Type: automatic - speech - recognition
  • Dataset:
    • Name: CommonVoice Corpus 14.0 (Spanish)
    • Type: mozilla - foundation/common_voice_14.0
    • Config: es
    • Split: test
    • Args:
      • Language: es
  • Metrics:
    • Name: Test WER
    • Type: wer
    • Value: '13.28'

📄 License

This project is licensed under the apache - 2.0 license.

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.

@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}
}