Add model card (README.md)

README.md

@@ -1,21 +1,69 @@
 ---
+language:
+  - multilingual
 license: cc-by-nc-4.0
-base_model: facebook/mms-lid-126
 tags:
-  - coreml
   - language-identification
+  - coreml
+  - ios
   - audio
   - wav2vec2
+  - mms-lid
+datasets:
+  - mms-lid
 ---
 
-# 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](https://huggingface.co/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](https://huggingface.co/aoiandroid/mms-lid-126-coreml-4bit) | 4-bit palettized (smaller, ANE-friendly) |
+| [mms-lid-126-coreml-int8](https://huggingface.co/aoiandroid/mms-lid-126-coreml-int8) | INT8 quantized |
+
+## Related repos (other language counts)
+
+| Languages | Core ML |
+|-----------|---------|
+| 126 | **this repo** |
+| 256 | [mms-lid-256-coreml](https://huggingface.co/aoiandroid/mms-lid-256-coreml) |
+| 512 | [mms-lid-512-coreml](https://huggingface.co/aoiandroid/mms-lid-512-coreml) |
 
-CoreML export of [facebook/mms-lid-126](https://huggingface.co/facebook/mms-lid-126) for iOS/macOS.
+## Citation
 
-- **mms_lid.mlmodel**: CoreML Neural Network (fixed 10s @ 16 kHz mono input, logits output).
-- **mms_lid_id2label.json**: Language ID to label mapping.
+```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}
+}
+```
 
-Input: raw waveform float32, shape `(1, 160000)` (16 kHz, 10 seconds).  
-Output: `logits` shape `(1, 126)`; use `argmax` then `id2label[id]` for language code.
+## License
 
-See the conversion repo docs for full input/output spec.
+CC-BY-NC-4.0 (inherited from MMS-LID).