lucasnewman / nanospeechLinks
A simple, hackable text-to-speech system in PyTorch and MLX
☆184Updated 4 months ago
Alternatives and similar repositories for nanospeech
Users that are interested in nanospeech are comparing it to the libraries listed below
Sorting:
- SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on On…☆224Updated 7 months ago
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆71Updated 4 months ago
- ☆343Updated 2 months ago
- Collection of Open Source Speech Data☆163Updated 2 months ago
- ☆62Updated last year
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.☆133Updated 2 months ago
- [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆140Updated 7 months ago
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆130Updated 4 months ago
- Very fast, accurate speaker diarization☆189Updated last week
- Official implementation of the TTS model Lina-Speech☆175Updated 11 months ago
- Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX☆20Updated last year
- ☆85Updated last year
- Open TTS models, built for streaming on the edge☆44Updated 9 months ago
- Speaker Diarization with Transformers☆69Updated 6 months ago
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated last year
- Open-source reproducible benchmarks from Argmax☆71Updated last week
- Audio tokenization, in the fastest way possible!☆53Updated last year
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆104Updated last year
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆193Updated 8 months ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆69Updated 2 months ago
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆29Updated last year
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆176Updated last month
- ☆30Updated 7 months ago
- Joint speech-language model - respond directly to audio!☆30Updated last year
- Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible…☆88Updated last month
- ☆275Updated last year
- VoiceBox neural network implementation☆110Updated last year
- ☆156Updated last week
- DACVAE☆124Updated this week
- Joint speech-language model - respond directly to audio!☆372Updated last year