Massively multilingual pronunciation mining
-
Updated
Jun 2, 2024 - Python
Massively multilingual pronunciation mining
Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.
An easy to use react component for the Web Speech API.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Data manipulation and transformation for audio signal processing, powered by PyTorch
VITS-based Voice Conversion focused on simplicity, quality and performance.
For this project is the setup for the Text To Speech.
A ggml (C++) re-implementation of tortoise-tts. Under construction and seeking contributors.
SharpSpeech is free, local and open source way to speech and wake word recognition.
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Monorepo for Transcribe.js
Tools for handling speech data in machine learning projects.
🚀 Framework for seamless fine-tuning of Whisper model on a multi-lingual dataset and deployment to prod.
General Speech Restoration
Add a description, image, and links to the speech topic page so that developers can more easily learn about it.
To associate your repository with the speech topic, visit your repo's landing page and select "manage topics."