Meta AI announces Massive Multilingual Speech code, models for 1000+ languages

Meta AI announces Massive Multilingual Speech code, models for 1000+ languages

by

Send to HN

The Massively Multilingual Speech (MMS) project expands speech technology from about 100 languages to over 1,000 by building a single multilingual speech recognition model supporting over 1,100 languages (more than 10 times as many as before), language identification models able to identify over 4,000 languages (40 times more than before), pretrained models supporting over 1,400 languages, and text-to-speech models for over 1,100 languages. Our goal is to make it easier for people to access information and to use devices in their preferred language.

You can find details in the paper Scaling Speech Technology to 1000+ languages and the blog post.

An overview of the languages covered by MMS can be found here.

Pretrained models

Example commands to finetune the pretrained models can be found here.

Finetuned models

ASR

TTS

  1. Download the list of iso codes of 1107 languages.
  2. Find the iso code of the target language and download the checkpoint. Each folder contains 3 files: G_100000.pth, config.json, vocab.txt. The G_100000.pth is the generator trained for 100K updates, config.json is the training config, vocab.txt is the vocabulary for the TTS model.

# Examples:
wget https://dl.fbaipublicfiles.com/mms/tts/eng.tar.gz # English (eng)
wget https://dl.fbaipublicfiles.com/mms/tts/azj-script_latin.tar.gz # North Azerbaijani (azj-script_latin)

LID

Commands to run inference

ASR

Run this command to transcribe one or more audio files:

cd /path/to/fairseq-py/
python examples/mms/asr/infer/mms_infer.py --model "/path/to/asr/model" --lang lang_code --audio "/path/to/audio_1.wav" "/path/to/audio_1.wav"

For more advance configuration and calculate CER/WER, you could prepare manifest folder by creating a folder with this format:

Followed by command below:

Available options:

  • To get the raw character-based output, user can change to common_eval.post_process=none

  • To maximize GPU efficiency or avoid out-of-memory (OOM), user can tune dataset.max_tokens=??? size

  • To run language model decoding, install flashlight python bindings using

    git clone --recursive git@github.com:flashlight/flashlight.git
cd flashlight; 
git checkout 035ead6efefb82b47c8c2e643603e87d38850076 
cd bindings/python 
python3 setup.py install

    Train a KenLM language model and prepare a lexicon file in this format.

    We typically sweep lmweight in the range of 0 to 5 and wordscore in the range of -3 to 3. The output directory will contain the reference and hypothesis outputs from decoder.

    For decoding with character-based language models, use empty lexicon file (decoding.lexicon=), decoding.unitlm=True and sweep over decoding.silweight instead of wordscore.

TTS

Note: clone and install VITS before running inference.

## English TTS
$ PYTHONPATH=$PYTHONPATH:/path/to/vits python examples/mms/tts/infer.py --model-dir /path/to/model/eng 
--wav ./example.wav --txt "Expanding the language coverage of speech technology 
has the potential to improve access to information for many more people"

## Maithili TTS
$ PYTHONPATH=$PYTHONPATH:/path/to/vits python examples/mms/tts/infer.py --model-dir /path/to/model/mai 
--wav ./example.wav --txt "मुदा आइ धरि ई तकनीक सौ सं किछु बेसी भाषा तक सीमित छल जे सात हजार  
सं बेसी ज्ञात भाषाक एकटा अंश अछी"

example.wav contains synthesized audio for the language.

LID

Prepare two files in this format

#/path/to/manifest.tsv
/
/path/to/audio1.wav
/path/to/audio2.wav
/path/to/audio3.wav

# /path/to/manifest.lang
eng 1
eng 1
eng 1

Download model and the corresponding dictionary file for the LID model.
Use the following command to run inference –

The above command assumes there is a file named dict.lang.txt in /path/to/dict/l126/. /predictions.txt will contain the predictions from the model for the audio files in manifest.tsv.

Forced Alignment Tooling

We also developed an efficient forced alignment algorithm implemented on GPU which is able to process very long audio files. This algorithm is open sourced and we provide instructions on how to use it here. We also open source a multilingual alignment model trained on 31K hours of data in 1,130 languages, as well as text normalization scripts.

The MMS code and model weights are released under the CC-BY-NC 4.0 license.

BibTeX:

@article{pratap2023mms,
  title={Scaling Speech Technology to 1,000+ Languages},
  author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli},
  journal={arXiv},
  year={2023}
}

Read More

Leave a Comment