Instructions to use red-kit/meeting-avatar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- CosyVoice
How to use red-kit/meeting-avatar with CosyVoice:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
7 days ago
-
LLM brain: Groq llama-3.1-8b-instant @ api.groq.com/openai/v1
Verified signature79842ae -
Correct stale Space claims; document slim-image + bucket deployment for HF Spaces
Verified signature19a9e34 -
Pin to single GPU (CUDA_VISIBLE_DEVICES=0): multi-GPU hosts OOM the boot-time model load; stack is single-GPU by design
Verified signature5eadf1b -
Hardware findings: 2x-a10g multi-GPU host OOMs without the single-GPU pin (now baked in); a10g-large marked unverified
Verified signature373f9c7 -
Correct Space hardware guidance (l40s/a10g-large, a10g-small OOM warning); add demo Space link and RAM requirement
Verified signature39cea70 -
Cap build parallelism to avoid OOM on memory-limited builders (caught by Space build)
Verified signature68ec264 -
Fix build: libavswscale-dev does not exist in Ubuntu 22.04, correct package is libswscale-dev (caught by Space build)
Verified signature26f0416 -
README: GPU smoke verification results + fixed-bug inventory
Verified signature71ff2b0 -
smoke: follow 307 redirect, 20-min readiness window, readable logs
Verified signature7e3368e -
smoke: patch upstream cosyvoice warmup call (stream=True keyword)
Verified signaturee2ac997 -
Dockerfile: patch upstream cosyvoice warmup call at build time
Verified signature710ddfd -
config: 48k stand-in voice path
Verified signatured45674d -
smoke: resample stand-in voice to 48k before boot
Verified signature90019d0 -
config: 48k stand-in voice path
Verified signature8a978c0 -
Dockerfile: resample stand-in voice to 48k at build time
Verified signature9c4f40a
8 days ago
-
config: fix stand-in voice ref path to submodule asset
Verified signature0dc6729 -
config: fix stand-in voice ref path to submodule asset
Verified signaturebbe91cb -
smoke: kill full process tree on all exit paths
Verified signature913e528 -
smoke: pyarrow<16 pin + pre-boot CosyVoice import check
Verified signature0fd0220 -
Dockerfile: pyarrow<16 pin (numpy1-compatible)
Verified signaturea1d2054 -
Dockerfile: --no-sync on post-install steps
Verified signatureaae61eb -
smoke: --no-sync on post-install uv runs (upgrade no longer reverted)
Verified signature0c535cb -
Dockerfile: typing_extensions>=4.14 fix from GPU smoke test
Verified signature3402560 -
smoke: typing_extensions fix + correct readiness grep + traceback fast-fail
Verified signature68a06cb -
smoke: bootstrap pip via ensurepip (base image lacks pip)
Verified signaturebbd43f6 -
smoke: install python3.11 via deadsnakes to match Dockerfile
Verified signaturef842b68 -
docs: face/voice collection spec + consent/legal
Verified signaturee532dba -
script: GPU end-to-end boot verification
Verified signaturec4ce248 -
Dockerfile: pinned OpenAvatarChat + MuseTalk + local CosyVoice2, weights baked in
Verified signature230f145 -
compose: self-host on any CUDA 12.8 host
Verified signature3784704 -
config: MuseTalk production pipeline
Verified signature5714994 -
README: pipeline, deploy options, personalization guide
Verified signature7b02b71 -
config: LiteAvatar lightweight fallback
Verified signaturee5217b4 -
docs: Zoom/Meet/Teams/LiveKit bridge routes + latency budget
Verified signature88da9d7 -
initial commit
Verified signature90db54d