Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,92 @@
+---
+license: mit
+language:
+  - multilingual
+tags:
+  - g2p
+  - grapheme-to-phoneme
+  - byt5
+  - mlx
+  - apple-silicon
+  - ipa
+  - phonetics
+library_name: mlx
+base_model: charsiu/g2p_multilingual_byT5_tiny_16_layers_100
+pipeline_tag: text-generation
+---
+
+# g2p-multilingual-byT5-tiny-mlx
+
+MLX-compatible weights for [charsiu/g2p_multilingual_byT5_tiny_16_layers_100](https://huggingface.co/charsiu/g2p_multilingual_byT5_tiny_16_layers_100) — a ByT5-based multilingual grapheme-to-phoneme converter supporting 100 languages.
+
+Converted from PyTorch to SafeTensors format for use with [mlx-swift](https://github.com/ml-explore/mlx-swift) and [MLX](https://github.com/ml-explore/mlx).
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| Architecture | T5ForConditionalGeneration (ByT5) |
+| Parameters | 20.8M |
+| Encoder layers | 12 |
+| Decoder layers | 4 |
+| d_model | 256 |
+| d_ff | 1024 |
+| Vocab size | 384 (byte-level) |
+| Format | SafeTensors (float32) |
+| Size | ~83 MB |
+
+## Performance
+
+| Metric | Score |
+|---|---|
+| PER (Phoneme Error Rate) | 0.096 |
+| WER (Word Error Rate) | 0.281 |
+
+## Usage with CharsiuG2PKit (Swift)
+
+```swift
+import CharsiuG2PKit
+
+let g2p = try G2P(modelDirectory: modelURL)
+let ipa = g2p.convert("hello", language: "eng-us")
+// "ˈhɛɫoʊ"
+```
+
+See [CharsiuG2PKit](https://github.com/beshkenadze/CharsiuG2PKit) for full documentation.
+
+## Usage with Python MLX
+
+```python
+import mlx.core as mx
+from mlx.utils import tree_unflatten
+from safetensors import safe_open
+
+tensors = {}
+with safe_open("model.safetensors", framework="numpy") as f:
+    for key in f.keys():
+        tensors[key] = mx.array(f.get_tensor(key))
+```
+
+## Conversion
+
+Converted from `pytorch_model.bin` using:
+```bash
+uv run scripts/convert_weights.py --model charsiu/g2p_multilingual_byT5_tiny_16_layers_100
+```
+
+Shared tensor aliases (`encoder.embed_tokens.weight`, `decoder.embed_tokens.weight`) are deduplicated — only `shared.weight` is kept.
+
+## Citation
+
+```bibtex
+@inproceedings{zhu2022byt5,
+  title={ByT5 model for massively multilingual grapheme-to-phoneme conversion},
+  author={Zhu, Jian and Zhang, Cong and Jurgens, David},
+  booktitle={Interspeech},
+  year={2022}
+}
+```
+
+## License
+
+MIT