Wav2vec2 FR 7K Large

🚀 LeBenchmark: wav2vec2 large model trained on 7K hours of French speech

LeBenchmark offers an ensemble of pre - trained wav2vec2 models on various French datasets, including spontaneous, read, and broadcasted speech. It has two versions, where the later version (LeBenchmark 2.0) is an extended one compared to the first version in terms of both the number of pre - trained self - supervised learning (SSL) models and the number of downstream tasks. For more details on the different benchmarks for evaluating wav2vec2 models, refer to our paper: LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self - supervised Representations of French Speech

✨ Features

Model and data descriptions

We've released four different models available under our HuggingFace organization. Four wav2vec2 architectures Light, Base, Large, and xLarge are paired with our small (1K), medium (3K), large (7K), and extra - large (14K) corpora. In brief:

Lebenchmark 2.0

• [wav2vec2 - FR - 14K - xlarge](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 14K - xlarge): xLarge wav2vec2 trained on 14K hours of French speech (5.4K Males / 2.4K Females / 6.8K unknown).
• [wav2vec2 - FR - 14K - large](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 14K - large): Large wav2vec2 trained on 14K hours of French speech (5.4K Males / 2.4K Females / 6.8K unknown).
• [wav2vec2 - FR - 14K - light](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 14K - light): Light wav2vec2 trained on 14K hours of French speech (5.4K Males / 2.4K Females / 6.8K unknown).

Lebenchmark

• [wav2vec2 - FR - 7K - large](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 7K - large): Large wav2vec2 trained on 7.6K hours of French speech (1.8K Males / 1.0K Females / 4.8K unknown).
• [wav2vec2 - FR - 7K - base](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 7K - base): Base wav2vec2 trained on 7.6K hours of French speech (1.8K Males / 1.0K Females / 4.8K unknown).
• [wav2vec2 - FR - 3K - large](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 3K - large): Large wav2vec2 trained on 2.9K hours of French speech (1.8K Males / 1.0K Females / 0.1K unknown).
• [wav2vec2 - FR - 3K - base](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 3K - base): Base wav2vec2 trained on 2.9K hours of French speech (1.8K Males / 1.0K Females / 0.1K unknown).
• [wav2vec2 - FR - 2.6K - base](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 2.6K - base): Base wav2vec2 trained on 2.6K hours of French speech (no spontaneous speech).
• [wav2vec2 - FR - 1K - large](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 1K - large): Large wav2vec2 trained on 1K hours of French speech (0.5K Males / 0.5K Females).
• [wav2vec2 - FR - 1K - base](https://huggingface.co/LeBenchmark/wav2vec2 - FR - 1K - base): Base wav2vec2 trained on 1K hours of French speech (0.5K Males / 0.5K Females).

📚 Documentation

Intended uses & limitations

Pre - trained wav2vec2 models are distributed under the Apache - 2.0 license. Thus, they can be extensively reused without strict limitations. However, benchmarks and data might be associated with corpora that are not fully open - sourced.

Fine - tune with Fairseq for ASR with CTC

Since our wav2vec2 models were trained with Fairseq, they can be used in the various tools provided by Fairseq to fine - tune the model for ASR with CTC. The full procedure is nicely summarized in [this blogpost](https://huggingface.co/blog/fine - tune - wav2vec2 - english).

Please note that due to the nature of CTC, speech - to - text results are not expected to be state - of - the - art. Moreover, future features may emerge depending on the involvement of Fairseq and HuggingFace in this area.

Integrate to SpeechBrain for ASR, Speaker, Source Separation ...

Pre - trained wav2vec models have recently become popular. Meanwhile, the SpeechBrain toolkit has emerged, offering a new and simpler way to handle state - of - the - art speech and deep - learning technologies.

Although it is currently in beta, SpeechBrain provides two different ways to nicely integrate wav2vec2 models trained with Fairseq, i.e., our LeBenchmark models!

1. Extract wav2vec2 features on - the - fly (with a frozen wav2vec2 encoder) to be combined with any speech - related architecture. Examples include: End - to - End (E2E) ASR with CTC + Attention + Language Models; Speaker Recognition or Verification, Source Separation...
2. Experimental: To fully leverage wav2vec2, the best approach is to fine - tune the model while training your downstream task. This is easily achievable within SpeechBrain by simply turning on a flag. Therefore, our wav2vec2 models can be fine - tuned while training your preferred ASR pipeline or Speaker Recognizer.

If interested, simply follow this tutorial

📄 License

The pre - trained wav2vec2 models are distributed under the Apache - 2.0 license.

Referencing LeBenchmark

@misc{parcollet2023lebenchmark,
      title={LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self - supervised Representations of French Speech}, 
      author={Titouan Parcollet and Ha Nguyen and Solene Evain and Marcely Zanon Boito and Adrien Pupier and Salima Mdhaffar and Hang Le and Sina Alisamir and Natalia Tomashenko and Marco Dinarelli and Shucong Zhang and Alexandre Allauzen and Maximin Coavoux and Yannick Esteve and Mickael Rouvier and Jerome Goulian and Benjamin Lecouteux and Francois Portet and Solange Rossato and Fabien Ringeval and Didier Schwab and Laurent Besacier},
      year={2023},
      eprint={2309.05472},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}