latishab / turnsenseLinks
A lightweight end-of-utterance detection model fine-tuned on SmolLM2-135M, optimized for Raspberry Pi and low-power devices.
☆38Updated last month
Alternatives and similar repositories for turnsense
Users that are interested in turnsense are comparing it to the libraries listed below
Sorting:
- Open-source reproducible benchmarks from Argmax☆73Updated last week
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.☆135Updated 2 months ago
- A curated list of awesome voice activity detection☆70Updated last year
- Open TTS models, built for streaming on the edge☆44Updated 9 months ago
- ☆19Updated 9 months ago
- Joint speech-language model - respond directly to audio!☆30Updated last year
- [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆140Updated 7 months ago
- Audio tokenization, in the fastest way possible!☆53Updated last year
- On-device voice activity detection (VAD) powered by deep learning☆238Updated last week
- ☆156Updated 2 weeks ago
- LSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances …☆83Updated 6 months ago
- Putting flows on top of neural transducers for better TTS☆64Updated 2 weeks ago
- Voice Activity Projection Models: Self-supervised learning of Turn-taking Events☆89Updated last year
- Official implementation of the TTS model Lina-Speech☆175Updated 11 months ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆69Updated 2 months ago
- VoiceBench: Benchmarking LLM-Based Voice Assistants☆311Updated 2 weeks ago
- ☆85Updated last year
- ☆58Updated last year
- TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog☆60Updated last year
- Collection of Open Source Speech Data☆163Updated 2 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆249Updated 9 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆19Updated last year
- ☆345Updated 2 months ago
- LongCat Audio Tokenizer and Detokenizer☆263Updated last week
- Add n-gram and large language model (LLM) support to Whisper models.☆39Updated 7 months ago
- Google's SoundStorm: Efficient Parallel Audio Generation☆131Updated 2 years ago
- We Speech Transcript based on LLM, in 300 lines of code.☆181Updated 6 months ago
- This project is to train an RWKV LLM for TTS generation which compatible to other TTS engine(like fish/cosy/chattts).☆91Updated 2 months ago
- ☆275Updated last year
- An LLM base TTS engine☆90Updated last year