NVIDIA Conformer-Transducer Large (ca-es)

Table of Contents

• Model Description
• Intended Uses and Limitations
• How to Get Started with the Model
• Training Details
• Citation
• Additional Information

Summary

The "stt_ca-es_conformer_transducer_large" is an acoustic model based on "NVIDIA/stt_es_conformer_transducer_large" suitable for Bilingual Catalan-Spanish Automatic Speech Recognition.

Model Description

This model transcribes speech in lowercase Catalan and Spanish alphabet including spaces, and was fine-tuned on a Bilingual ca-es dataset comprising of 7426 hours. It is a "large" variant of Conformer-Transducer, with around 120 million parameters. See the model architecture section and NeMo documentation for complete architecture details.

Intended Uses and Limitations

This model can be used for Automatic Speech Recognition (ASR) in Catalan and Spanish. It is intended to transcribe audio files in Catalan and Spanish to plain text without punctuation.

Installation

To use this model, install NVIDIA NeMo. We recommend you install it after you've installed the latest PyTorch version.

pip install nemo_toolkit['all']

For Inference

To transcribe audio in Catalan or in Spanish using this model, you can follow this example:

import nemo.collections.asr as nemo_asr

nemo_asr_model = nemo_asr.models.EncDecRNNTBPEModel.restore_from(model)
transcription = nemo_asr_model.transcribe([audio_path])[0].text
print(transcription)

Training Details

Training data

The model was trained on bilingual datasets in Catalan and Spanish, for a total of 7k hours. Including:

• Parlament-Parla-v3 (Only the anonymized version of the dataset is public. We trained the model with the non-anonymized version.)
• Corts Valencianes (Only the anonymized version of the dataset is public. We trained the model with the non-anonymized version.)
• 3cat
• IB3 (The datasets will be made accessible shortly.)
• Common Voice ca 17 Benchmark
• ciempiess light
• ciempiess fem
• ciempiess complementary
• ciempiess balance
• CHM150
• Tedx spanish
• librivox spanish
• Wikipedia spanish
• voxforge spanish
• Tele con ciencia
• Argentinian Spanish Speech Dataset
• Dimex100 light
• Glissando Spanish
• Herico
• Latino40
• Common voice 17 es

Training procedure

This model is the result of finetuning the base model "Nvidia/stt_es_conformer_transducer_large" by following this tutorial.

Citation

If this model contributes to your research, please cite the work:

@misc{conformer-transducer-BSC-2024,
      title={Bilingual ca-es ASR Model: stt_ca-es_conformer_transducer_large.}, 
      author={Messaoudi, Abir; Külebi, Baybars},
      organization={Barcelona Supercomputing Center},
      url={https://huggingface.co/projecte-aina/stt_ca-es_conformer_transducer_large},
      year={2024}
}

Additional Information

Author

The fine-tuning process was performed during 2024 in the Language Technologies Unit of the Barcelona Supercomputing Center by Abir Messaoudi.

For the Catalan Valencian data, we had the collaboration of CENID within the framework of the ILENIA project.

Contact

For further information, please send an email to langtech@bsc.es.

Copyright

Copyright(c) 2024 by Language Technologies Unit, Barcelona Supercomputing Center.

License

CC-BY-4.0

Funding

This work is funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project ILENIA with reference 2022/TL22/00215337.

The training of the model was possible thanks to the computing time provided by Barcelona Supercomputing Center through MareNostrum 5.