Fisher-Callhome-Spanish

Speech Translation on Fisher-Callhome Spanish recipe

This folder contains recipes for tokenization and speech translation with Fisher-Callhome Spanish, a 160-hour Spanish-English ST dataset.

Installing Extra Dependencies

Before proceeding, ensure you have installed the necessary additional dependencies. To do this, simply run the following command in your terminal:

pip install -r extra_requirements.txt

How to run

1- Train a tokenizer. The tokenizer takes in input the training translations and determines the subword units that will be used for the ST task, the auxiliary MT task.

cd Tokenizer
python train.py hparams/train_bpe_1k.yaml

2- Train the speech translator

cd ST/transformer
python train.py hparams/transformer.yaml

Performance summary

Results are reported in terms of sacrebleu.

hyperparams file	dev	dev2	test	ctc_weight	asr_weight	mt_weight	Model	GPUs
transformer.yaml	40.67	41.51	40.30	0	0	0	Not Avail.	2xRTX 2080 Ti 11GB
transformer.yaml	47.50	48.33	47.31	1	0.3	0	Model	2xRTX 2080 Ti 11GB
transformer.yaml	46.10	46.56	46.79	1	0.2	0.2	Not Avail.	2xRTX 2080 Ti 11GB
conformer.yaml	46.37	47.07	46.10	0	0	0	Not Avail.	2xRTX 2080 Ti 11GB
conformer.yaml	48.09	48.19	48.04	1	0.3	0	Model	1xTesla A100 (works with 2xRTX 2080 Ti)

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{speechbrainV1,
  title={Open-Source Conversational AI with SpeechBrain 1.0},
  author={Mirco Ravanelli and Titouan Parcollet and Adel Moumen and Sylvain de Langen and Cem Subakan and Peter Plantinga and Yingzhi Wang and Pooneh Mousavi and Luca Della Libera and Artem Ploujnikov and Francesco Paissan and Davide Borra and Salah Zaiem and Zeyu Zhao and Shucong Zhang and Georgios Karakasidis and Sung-Lin Yeh and Pierre Champion and Aku Rouhe and Rudolf Braun and Florian Mai and Juan Zuluaga-Gomez and Seyed Mahed Mousavi and Andreas Nautsch and Xuechen Liu and Sangeet Sagar and Jarod Duret and Salima Mdhaffar and Gaelle Laperriere and Mickael Rouvier and Renato De Mori and Yannick Esteve},
  year={2024},
  eprint={2407.00463},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2407.00463},
}
@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}
}