elyxlz / voxtralLinks
Voxtral: Convert Mistral into a end2end SpeechLM. No information bottleneck, preserves prosody, learns interruptions from data. Unlike GPT4o (closed) or Moshi (complex), it's open, simple, natural.
☆35Updated 8 months ago
Alternatives and similar repositories for voxtral
Users that are interested in voxtral are comparing it to the libraries listed below
Sorting:
- Open TTS models, built for streaming on the edge☆43Updated 7 months ago
- LongCat Audio Tokenizer and Detokenizer☆196Updated last week
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆128Updated 2 months ago
- ☆60Updated last month
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.☆111Updated last month
- ☆62Updated last year
- ☆190Updated 3 weeks ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆68Updated 2 weeks ago
- This is a repository that collects common audio noise reduction models, using Gradio to demonstrate the use of each model, which is very …☆47Updated 11 months ago
- Collection of Open Source Speech Data☆161Updated last month
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆15Updated last year
- A collection of optimized utilities for text-to-audio processing, enhancing both training and inference workflows. This repository contai…☆39Updated 7 months ago
- SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on On…☆220Updated 5 months ago
- Audio tokenization, in the fastest way possible!☆53Updated last year
- EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs☆40Updated last month
- ☆78Updated 3 weeks ago
- StyleTTS 2 Optimized Training Fork☆34Updated 9 months ago
- Official implementation of the TTS model Lina-Speech☆170Updated 10 months ago
- FLM-Audio is a audio-language subversion of RoboEgo/FLM-Ego -- an omnimodal model with native full duplexity.☆43Updated last month
- ☆22Updated 2 months ago
- [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆132Updated 5 months ago
- ☆40Updated 3 months ago
- Accompanying repository for the paper "DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions"☆35Updated last week
- Googleの音声復元モデルMiipher-2の再現実装の学習および推論コード。学習済みモデルも公開しています。☆25Updated 3 months ago
- This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaD…☆190Updated last month
- ☆31Updated 2 months ago
- VoiceBox neural network implementation☆110Updated last year
- Whisper Speaker Identification (WSI), a cutting-edge model for multilingual speaker identification.☆24Updated 7 months ago
- Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation☆297Updated last week