tarzain / crosstalkLinks
a simple system for 2-way interruptible voice interactions between human and LLM
☆30Updated last year
Alternatives and similar repositories for crosstalk
Users that are interested in crosstalk are comparing it to the libraries listed below
Sorting:
- Open TTS models, built for streaming on the edge☆44Updated 9 months ago
- Joint speech-language model - respond directly to audio!☆30Updated last year
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆69Updated 2 months ago
- Audio tokenization, in the fastest way possible!☆53Updated last year
- ☆62Updated last year
- A lightweight Python library for running TTS models with a unified API.☆21Updated 10 months ago
- SpeechPlus: Small LLM-Based Text-to-Speech Library 🚀☆20Updated 7 months ago
- ☆243Updated 3 weeks ago
- Collection of Open Source Speech Data☆164Updated 3 months ago
- ☆19Updated 10 months ago
- VoiceStar: Robust, Duration-controllable TTS that can Extrapolate☆306Updated 7 months ago
- A highly compressive and high-quality neural audio codec for speech models.☆204Updated last week
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆131Updated 5 months ago
- Speaker Diarization with Transformers☆69Updated 7 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆16Updated last year
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.☆138Updated 3 months ago
- Fast audio super resolution from 16khz to 48khz.☆167Updated last week
- ☆342Updated 4 months ago
- proof of concept conversation orchestrator with a speech-language model☆20Updated last year
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆181Updated 2 months ago
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆57Updated 7 months ago
- Voxtral: Convert Mistral into a end2end SpeechLM. No information bottleneck, preserves prosody, learns interruptions from data. Unlike GP…☆40Updated 10 months ago
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.☆46Updated 3 months ago
- A minimalistic automatic speech recognition streamlit based webapp powered by OpenAI's Whisper "State of the Art" models☆67Updated 3 years ago
- This public GitHub repository contains code for a fully self-hosted, on-premise transcription solution.☆53Updated last year
- Speaker diarization service☆25Updated 6 months ago
- The YouTube Text-To-Speech dataset is comprised of waveform audio extracted from YouTube videos alongside their English transcriptions☆52Updated 4 years ago
- ☆60Updated 3 weeks ago
- Train your own speech AI model from scratch☆128Updated 3 weeks ago
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆29Updated last year