docs: model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
pipeline_tag: text-to-speech
|
| 4 |
+
library_name: phoonnx
|
| 5 |
+
tags: [phoonnx, mms, vits, tts, multilingual]
|
| 6 |
+
---
|
| 7 |
+
# phoonnx-mms
|
| 8 |
+
Meta **MMS-TTS** voices for [phoonnx](https://github.com/TigreGotico/phoonnx) — VITS models covering ~1100+
|
| 9 |
+
languages. One voice per subfolder (`model.onnx` + native `config.json` +
|
| 10 |
+
tokenizer). Mirror/conversion of [facebook/mms-tts](https://huggingface.co/facebook/mms-tts)
|
| 11 |
+
and community MMS finetunes. Part of the [phoonnx community mirror](https://huggingface.co/collections/OpenVoiceOS/phoonnx-community-mirror-6a2204d302e0e7497870cd68).
|
| 12 |
+
|
| 13 |
+
License: **cc-by-nc-4.0** (MMS-TTS). Phonemization is grapheme/uroman-based per
|
| 14 |
+
the MMS pipeline. Loaded via the phoonnx voice index (`engine: transformers`).
|