asr-wav2vec2-orfeo-fr : LeBenchmark/wav2vec2-FR-7K-large fine-tuned on Orféo dataset

asr-wav2vec2-orfeo-fr is an Automatic Speech Recognition model fine-tuned on Orféo with LeBenchmark/wav2vec2-FR-7K-large as the pretrained wav2vec2 model.

The fine-tuned model achieves the following performance :

Release	Valid WER	Test WER	GPUs	Epochs
2023-09-08	23.24	23.29	4xV100 32GB	30

📝 Model Details

The ASR system is composed of:

• the Tokenizer (char) that transforms the input text into a sequence of characters ("cat" into ["c", "a", "t"]) and trained with the train transcriptions (train.tsv).
• the Acoustic model (wav2vec2.0 + DNN + CTC greedy decode). The pretrained wav2vec 2.0 model LeBenchmark/wav2vec2-FR-7K-large is combined with two DNN layers and fine-tuned on Orféo. The final acoustic representation is given to the CTC greedy decode.

We used recordings sampled at 16kHz (single channel). For training, we did not use audio files longer than 10 seconds to prevent memory issues.

💻 How to transcribe a file with the model

Install and import speechbrain

pip install speechbrain

from speechbrain.inference.ASR import EncoderASR

Pipeline

def transcribe(audio, model):
    return model.transcribe_file(audio).lower()


def save_transcript(transcript, audio, output_file):
    with open(output_file, 'w', encoding='utf-8') as file:
        file.write(f"{audio}\t{transcript}\n")


def main():
    model = EncoderASR.from_hparams("Propicto/asr-wav2vec2-orfeo-fr", savedir="tmp/")
    transcript = transcribe(audio, model)
    save_transcript(transcript, audio, "out.txt")

⚙️ Training Details

Training Data

We use train/validation/test splits with an 80/10/10 distribution, corresponding to:

	Train	Valid	Test
# utterances	231,374	28,796	29,009
# hours	147.26	18.43	13.95

Training Procedure

We follow the training procedure provided in the ASR-CTC speechbrain recipe.

Training Hyperparameters

Refer to the hyperparams.yaml file to get the hyperparameters' information.

Training time

With 4xV100 32GB, the training took ~ 22 hours.

Libraries

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}},
  }

💡 Information

• Developed by: Cécile Macaire
• Funded by [optional]: GENCI-IDRIS (Grant 2023-AD011013625R1) PROPICTO ANR-20-CE93-0005
• Language(s) (NLP): French
• License: Apache-2.0
• Finetuned from model: LeBenchmark/wav2vec2-FR-7K-large

📌 Citation

@inproceedings{macaire24_interspeech,
  title     = {Towards Speech-to-Pictograms Translation},
  author    = {Cécile Macaire and Chloé Dion and Didier Schwab and Benjamin Lecouteux and Emmanuelle Esperança-Rodier},
  year      = {2024},
  booktitle = {Interspeech 2024},
  pages     = {857--861},
  doi       = {10.21437/Interspeech.2024-490},
  issn      = {2958-1796},
}