Instructions to use naklitechie/mms-tts-te-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use naklitechie/mms-tts-te-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-to-audio', 'naklitechie/mms-tts-te-ONNX');
MMS-TTS Telugu — ONNX
Verbatim ONNX export of facebook/mms-tts-tel
for in-browser inference via transformers.js
or onnxruntime-web.
This bundle was produced by the onnx-conversion pipeline at
scripts/seq2seq/03_mms_batch_export.py so the Ghoshana
browser app can ship MMS-TTS coverage for Telugu without depending on
a system voice install.
The MMS family from Massively Multilingual Speech
covers 1107+ languages but only ~12 of those have community ONNX exports
(Xenova mostly), with kn (Kannada) at onnx-community. This repo fills
in the rest of the Telugu gap.
License
CC-BY-NC-4.0 (inherited from the upstream facebook/mms-tts-tel).
- Downloads last month
- 18
Model tree for naklitechie/mms-tts-te-ONNX
Base model
facebook/mms-tts-tel