tincans-ai / gazelle
Joint speech-language model - respond directly to audio!
☆370Updated 8 months ago
Alternatives and similar repositories for gazelle:
Users that are interested in gazelle are comparing it to the libraries listed below
- ☆201Updated 9 months ago
- On-device intelligence.☆307Updated this week
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆210Updated this week
- ☆591Updated last week
- ☆277Updated 9 months ago
- Whisper with Medusa heads☆821Updated last month
- ☆480Updated 9 months ago
- An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine☆376Updated 6 months ago
- A ggml (C++) re-implementation of tortoise-tts☆178Updated 7 months ago
- An API to transcribe audio with OpenAI's Whisper Large v3!☆254Updated 4 months ago
- Collection of Open Source Speech Data☆152Updated 4 months ago
- Official implementation of "WhisperNER: Unified Open Named Entity and Speech Recognition"☆180Updated last month
- ☆352Updated 6 months ago
- Joint speech-language model - respond directly to audio!☆30Updated 10 months ago
- ☆254Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆224Updated 10 months ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆891Updated 4 months ago
- Video+code lecture on building nanoGPT from scratch☆66Updated 9 months ago
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆156Updated this week
- 🐮📢 The first AI voice assistant that interrupts *you*☆140Updated 6 months ago
- Whisper realtime streaming for long speech-to-text transcription and translation☆113Updated last year
- Open source conversation framework and visual editor for structured Pipecat dialogues☆258Updated this week
- G2P☆174Updated this week
- End-to-end platform for building voice first multimodal agents☆414Updated 4 months ago
- ☆266Updated 9 months ago
- Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens☆480Updated last year
- Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate☆515Updated 4 months ago
- Efficient approach to speaker diarization using voice characteristics extraction☆92Updated 11 months ago
- 🐍 🤖 Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloning☆155Updated 8 months ago
- ☆155Updated last year