modelscope
modelscope's tracked open-source repos, sorted by stars.
- #1
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
★ 20,072+108Star change over the last 7 days - #2
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 15,400+76Star change over the last 7 days - #3
Enjoy the magic of Diffusion models!
★ 13,019+45Star change over the last 7 days - #4★ 9,508+4Star change over the last 7 days
- #5
ModelScope: bring the notion of Model-as-a-Service to life.
★ 9,117+19Star change over the last 7 days - #6
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
★ 6,197+25Star change over the last 7 days - #7
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
★ 4,449+19Star change over the last 7 days - #8★ 4,372+6Star change over the last 7 days
- #9
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
★ 3,331+47Star change over the last 7 days - #10
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
★ 3,125+13Star change over the last 7 days - #11
AgentEvolver: Towards Efficient Self-Evolving Agent System
★ 1,549+10Star change over the last 7 days - #12★ 1,481+5Star change over the last 7 days
- #13★ 1,203+4Star change over the last 7 days
- #14
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
★ 550+0Star change over the last 7 days
