thevoicecompany / gazelle-train
Joint speech-language model - respond directly to audio!
☆30Updated 11 months ago
Alternatives and similar repositories for gazelle-train:
Users that are interested in gazelle-train are comparing it to the libraries listed below
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆62Updated 3 weeks ago
- Open TTS models, built for streaming on the edge☆41Updated last month
- ☆62Updated 9 months ago
- Speaker Diarization with Transformers☆64Updated 11 months ago
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated 11 months ago
- Audio tokenization, in the fastest way possible!☆51Updated 8 months ago
- ☆206Updated last month
- Open-source and reproducible benchmarks for Speaker Diarization☆23Updated 2 weeks ago
- VoiceBox neural network implementation☆106Updated 9 months ago
- Collection of Open Source Speech Data☆153Updated 5 months ago
- ☆19Updated this week
- Google's SoundStorm: Efficient Parallel Audio Generation☆132Updated last year
- A simple, hackable text-to-speech system in PyTorch and MLX☆154Updated 2 months ago
- a simple system for 2-way interruptible voice interactions between human and LLM☆28Updated last year
- Speaker diarization service☆21Updated 3 weeks ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆14Updated 10 months ago
- proof of concept conversation orchestrator with a speech-language model☆19Updated 6 months ago
- A lightweight Python library for running TTS models with a unified API.☆18Updated 2 months ago
- ☆92Updated this week
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆95Updated 6 months ago
- StyleTTS 2 Optimized Training Fork☆27Updated 3 months ago
- A synthetic story narration dataset to study small audio LMs.☆32Updated last year
- Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX☆20Updated 6 months ago
- Whisper Speaker Identification (WSI), a cutting-edge model for multilingual speaker identification.☆16Updated last month
- I publish my weekly research here☆14Updated 2 weeks ago
- Supervoice diffusion enhance☆26Updated 9 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆17Updated 5 months ago
- Official repository of the IEEE SLT 2024 paper "Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT"☆38Updated 2 weeks ago
- LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆101Updated 2 weeks ago
- ☆24Updated last week