revdotcom / reverbLinks
Open source inference code for Rev's model
☆435Updated 9 months ago
Alternatives and similar repositories for reverb
Users that are interested in reverb are comparing it to the libraries listed below
Sorting:
- A toolkit for speaker diarization.☆384Updated 2 weeks ago
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection☆889Updated 8 months ago
- A lightweight end-to-end text-to-speech model☆126Updated 11 months ago
- ☆473Updated 8 months ago
- We Speech Transcript based on LLM, in 300 lines of code.☆183Updated 7 months ago
- Speech Diarization for scrum automation☆111Updated 2 years ago
- Whisper with Medusa heads☆865Updated 5 months ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆651Updated last week
- ☆359Updated last year
- A Fast TTS Engine☆611Updated last year
- G2P☆400Updated 5 months ago
- Efficient approach to speaker diarization using voice characteristics extraction☆106Updated 7 months ago
- Running the F5-TTS by ONNX Runtime☆191Updated 3 weeks ago
- Have a natural voice conversation with an LLM☆261Updated 2 weeks ago
- Whisper realtime streaming for long speech-to-text transcription and translation☆121Updated 2 years ago
- Live-Transcription (STT) with Whisper PoC☆202Updated last year
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆925Updated last year
- ☆167Updated last year
- Implementation of F5-TTS in MLX☆605Updated 10 months ago
- Text to speech alignment using CTC forced alignment☆421Updated 2 months ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆830Updated 2 months ago
- OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.☆474Updated 2 months ago
- Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯☆886Updated last month
- ☆258Updated last year
- ☆536Updated 4 months ago
- Interface for OuteTTS models.☆1,421Updated 7 months ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆695Updated 2 months ago
- Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation☆426Updated 2 months ago
- ☆386Updated last year
- FastAPI service on top of WhisperX☆169Updated this week