Language Identification from Speech Recordings with ECAPA embeddings on CommonLanguage

This repository provides all the necessary tools to perform language identification from speech recordings with SpeechBrain. The system uses a model pretrained on the CommonLanguage dataset (45 languages). You can download the dataset here The provided system can recognize the following 45 languages from short speech recordings:

Arabic, Basque, Breton, Catalan, Chinese_China, Chinese_Hongkong, Chinese_Taiwan, Chuvash, Czech, Dhivehi, Dutch, English, Esperanto, Estonian, French, Frisian, Georgian, German, Greek, Hakha_Chin, Indonesian, Interlingua, Italian, Japanese, Kabyle, Kinyarwanda, Kyrgyz, Latvian, Maltese, Mongolian, Persian, Polish, Portuguese, Romanian, Romansh_Sursilvan, Russian, Sakha, Slovenian, Spanish, Swedish, Tamil, Tatar, Turkish, Ukrainian, Welsh

For a better experience, we encourage you to learn more about SpeechBrain . The given model performance on the test set is:

Pipeline description

This system is composed of an ECAPA model coupled with statistical pooling. A classifier, trained with Categorical Cross-Entropy Loss, is applied on top of that.

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 classify_file if needed. Make sure your input tensor is compliant with the expected sampling rate if you use encode_batch and classify_batch .

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain .

Perform Language Identification from Speech Recordings

import torchaudio
from speechbrain.pretrained import EncoderClassifier
classifier = EncoderClassifier.from_hparams(source="speechbrain/lang-id-commonlanguage_ecapa", savedir="pretrained_models/lang-id-commonlanguage_ecapa")
# Italian Example
out_prob, score, index, text_lab = classifier.classify_file('speechbrain/lang-id-commonlanguage_ecapa/example-it.wav')
print(text_lab)

# French Example
out_prob, score, index, text_lab = classifier.classify_file('speechbrain/lang-id-commonlanguage_ecapa/example-fr.wav')
print(text_lab)

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 (a02f860e). To train it from scratch follow these steps:

git clone https://github.com/speechbrain/speechbrain/

cd speechbrain
pip install -r requirements.txt
pip install -e .

cd recipes/CommonLanguage/lang_id
python train.py hparams/train_ecapa_tdnn.yaml --data_folder=your_data_folder

You can find our training results (models, logs, etc) here .

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

  author    = {Brecht Desplanques and
               Jenthe Thienpondt and
               Kris Demuynck},
  editor    = {Helen Meng and
               Bo Xu and
               Thomas Fang Zheng},
  title     = {{ECAPA-TDNN:} Emphasized Channel Attention, Propagation and Aggregation
               in {TDNN} Based Speaker Verification},
  booktitle = {Interspeech 2020},
  pages     = {3830--3834},
  publisher = {{ISCA}},
  year      = {2020},
}

Citing SpeechBrain

Please, cite SpeechBrain if you use it for your research or business.

@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}
}