Instructions to use internetoftim/speecht5_tts-pld-fil-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use internetoftim/speecht5_tts-pld-fil-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-to-speech', 'internetoftim/speecht5_tts-pld-fil-ONNX');
speecht5_tts-pld-fil-ONNX
ONNX export of sapinsapin/speecht5_tts-pld-fil for in-browser
inference with Transformers.js
(WebGPU / WASM). Converted with the transformers.js conversion script
(python -m scripts.convert --quantize), which also produces quantized
variants (fp16, q8, int8, uint8, q4, bnb4) under onnx/.
Used as the default TTS model in the Can I AI? speech benchmark.
Usage (Transformers.js)
import { pipeline } from "@huggingface/transformers";
const pipe = await pipeline("text-to-speech", "internetoftim/speecht5_tts-pld-fil-ONNX");
- Downloads last month
- 8
Model tree for internetoftim/speecht5_tts-pld-fil-ONNX
Base model
sapinsapin/speecht5_tts-pld-fil