100% private on-device voice models for speech-to-text and meeting transcription on macOS
Repository Index
108,094 visible repositories in the index
1–5 of 5 · Most stars
Free & fast alternative to Wispr Flow
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
- chattts
- ssml
- tts
- chattts-forge
This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.