aoiandroid/mms-lid-126-coreml

MMS-LID 126 (Core ML)

Core ML conversion of MMS-LID (Massively Multilingual Speech - Language Identification) for 126 languages. Float16 model for on-device inference on iOS 17+ and macOS.

• Base model: facebook/mms-lid-126
• Format: Core ML (.mlpackage), float16
• Languages: 126 (ISO 639-3)

Contents

• mms_lid.mlpackage (or equivalent) – Core ML model
• labels.json or mms_lid_id2label.json – Index to language code mapping

Input / Output

• Input: 16 kHz mono float32 audio, 10 seconds (160,000 samples), e.g. input_values
• Output: Logits over 126 language classes; argmax gives the predicted language index. Map to ISO 639-3 using the labels file.

Usage (iOS / macOS)

1. Download this repo (e.g. via Hugging Face Hub or in-app download).
2. Load the .mlpackage with Core ML; feed 10 seconds of 16 kHz mono audio.
3. Take argmax of the logits output and look up the language code in labels.json or mms_lid_id2label.json.

Quantized variants (same language count)

Repo	Description
this repo	Float16 Core ML
mms-lid-126-coreml-4bit	4-bit palettized (smaller, ANE-friendly)
mms-lid-126-coreml-int8	INT8 quantized

Related repos (other language counts)

Languages	Core ML
126	this repo
256	mms-lid-256-coreml
512	mms-lid-512-coreml

Citation

@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}
}

License

CC-BY-NC-4.0 (inherited from MMS-LID).