---
language:
- fr
thumbnail: null
pipeline_tag: spoken-language-understanding
tags:
- CTC
- pytorch
- speechbrain
- hf-slu-leaderboard
license: apache-2.0
datasets:
- MEDIA
metrics:
- cver
- cer
- cher
model-index:
- name: slu-wav2vec2-ctc-MEDIA-full
  results:
  - task:
      name: Spoken Language Understanding
      type: spoken-language-understanding
    dataset:
      name: MEDIA
      type: MEDIA_slu_full
      config: fr
      split: test
      args:
        language: fr
    metrics:
    - name: Test ChER
      type: cher
      value: 7.78
    - name: Test CER
      type: cer
      value: 24.88
    - name: Test CVER
      type: cver
      value: 35.77
---

<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/>

# wav2vec 2.0 with CTC trained on MEDIA

This repository provides all the necessary tools to perform spoken language understanding
from an end-to-end system pretrained on MEDIA (French 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 ChER | Test CER | Test CVER | GPUs |
|:-------------:|:--------------:|:--------------:|:--------------:|:--------:|
| 22-02-23 | 7.78 | 24.88 | 35.77 | 1xV100 32GB |

## Pipeline description

This SLU system is composed of an acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([LeBenchmark/wav2vec2-FR-3K-large](https://huggingface.co/LeBenchmark/wav2vec2-FR-3K-large)) is combined with three DNN layers and finetuned on MEDIA.
The obtained final acoustic representation is given to the CTC 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
```

Please notice that we encourage you to read our tutorials and learn more about
[SpeechBrain](https://speechbrain.github.io).

### Transcribing and semantically annotating your own audio files (in French)

```python
from speechbrain.pretrained import EncoderASR

asr_model = EncoderASR.from_hparams(source="speechbrain/slu-wav2vec2-ctc-MEDIA-full", savedir="pretrained_models/slu-wav2vec2-ctc-MEDIA-full")
asr_model.transcribe_file('speechbrain/asr-wav2vec2-commonvoice-fr/example-fr.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. Download MEDIA related files:
- [Media ASR (ELRA-S0272)](https://catalogue.elra.info/en-us/repository/browse/ELRA-S0272/)
- [Media SLU (ELRA-E0024)](https://catalogue.elra.info/en-us/repository/browse/ELRA-E0024/)
- [channels.csv and concepts_full_relax.csv](https://drive.google.com/drive/u/1/folders/1z2zFZp3c0NYLFaUhhghhBakGcFdXVRyf)
4. Modify placeholders in hparams/train_hf_wav2vec_full.yaml:
```bash
data_folder = !PLACEHOLDER
channels_path = !PLACEHOLDER
concepts_path = !PLACEHOLDER
```
5. Run Training:
```bash
cd recipes/MEDIA/SLU/CTC/
python train_hf_wav2vec.py hparams/train_hf_wav2vec_full.yaml
```

You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1cZRRQ3Cc_ucXXlwYSJqB7pOl6KwZdo84?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