Cross-Product-Labs / csm_finetuneLinks
Finetune Sesame's CSM 1B model, for fun and profit
☆17Updated 7 months ago
Alternatives and similar repositories for csm_finetune
Users that are interested in csm_finetune are comparing it to the libraries listed below
Sorting:
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆57Updated 5 months ago
- Examples of using the llasa-tts models locally☆181Updated 6 months ago
- Sesame Converse - Real Time Conversations - Powered by Gemma 3☆64Updated 7 months ago
- ☆300Updated 2 months ago
- Unofficial WIP LoRa Finetuning repository for VibeVoice☆251Updated last month
- ☆23Updated last year
- ☆40Updated last year
- Create Unmute voice embeddings☆20Updated 3 months ago
- High-performance ASR tool using Faster Whisper, supporting custom models, multi-language transcription, and real-time processing feedback…☆10Updated last month
- VLLM Port of the Chatterbox TTS model☆329Updated 3 weeks ago
- Streaming and Fine-tuning for Chatterbox TTS☆212Updated 5 months ago
- ACE-Step: A Step Towards Music Generation Foundation Model☆45Updated 5 months ago
- ☆14Updated last year
- List of curated use cases built using Sesame's CSM 1B☆73Updated 5 months ago
- An open source real-time AI inference engine for seamless scaling☆20Updated 4 months ago
- finetune your florence2 model easy☆20Updated last year
- (Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on …☆107Updated 3 weeks ago
- SoTA open-source TTS☆115Updated 3 weeks ago
- SoTA open-source TTS☆107Updated 5 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆81Updated last year
- BeltOut: An open source pitch-perfect voice-to-voice timbre transfer model based on ChatterboxVC☆78Updated 3 months ago
- ☆19Updated last year
- Lightweight Gradio based WebUI for orpheusTTS - WSL / Linux [CUDA]☆104Updated 7 months ago
- A functioning Sesame CSM project with a desktop GUI - Real-time factor: 0.6x with 4070 Ti Super - Requires only 8GB VRAM☆69Updated 5 months ago
- ☆197Updated last month
- Unlimited-length talking video generation that supports image-to-video and video-to-video generation☆48Updated 2 months ago
- ☆127Updated 8 months ago
- ☆22Updated 2 months ago
- A pipeline parallel training script for LLMs.☆162Updated 6 months ago
- Open TTS models, built for streaming on the edge☆44Updated 7 months ago