rooms-solutions / csm-multilingualLinks
Multilingual extension of the SesameAILabs Conversational Speech Generation Model
☆26Updated 2 months ago
Alternatives and similar repositories for csm-multilingual
Users that are interested in csm-multilingual are comparing it to the libraries listed below
Sorting:
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆56Updated 2 weeks ago
- An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.☆53Updated this week
- ☆174Updated 2 weeks ago
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆254Updated 2 weeks ago
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆38Updated 2 weeks ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆91Updated 2 weeks ago
- A lightweight end-to-end text-to-speech model☆115Updated 3 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆230Updated 2 months ago
- ☆224Updated this week
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆170Updated last month
- A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.☆132Updated 11 months ago
- Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.☆94Updated last month
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelines☆94Updated last year
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆62Updated last week
- ☆227Updated 2 months ago
- VoiceBench: Benchmarking LLM-Based Voice Assistants☆211Updated 3 weeks ago
- VoiceStar: Robust, Duration-controllable TTS that can Extrapolate☆231Updated this week
- Speech To Speech: an effort for an open-sourced and modular GPT4-o☆62Updated 7 months ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆164Updated last month
- A lightweight, efficient variation of the StyleTTS 2 text‐to‐speech model.☆18Updated 2 weeks ago
- Efficient approach to speaker diarization using voice characteristics extraction☆94Updated last year
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆27Updated 7 months ago
- ASR + diarization model server with speculative decoding☆60Updated last year
- ☆174Updated last year
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆62Updated 6 months ago
- Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.☆56Updated last month
- On-device streaming text-to-speech engine powered by deep learning☆85Updated this week
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.☆36Updated last week
- Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)☆81Updated 11 months ago
- Service for testing out the new Qwen2.5 omni model☆49Updated last month