Spaces:

ebitlogix
/

Qwen-ASR-VLM-combined

Sleeping

App Files Files Community

Qwen-ASR-VLM-combined

164 kB

Ctrl+K

Ctrl+K

2 contributors

History: 15 commits

aspirant312's picture

Claude Opus 4.8 (1M context)

Serialize all vLLM access with a shared model_lock

2d8be5e about 1 month ago

data
Update data/lexicons.json about 2 months ago
.gitattributes

1.52 kB
Initial commit: Qwen3-ASR vLLM server (Chughtai variant), lexicons and project config 2 months ago
.gitignore

1.16 kB
Split into shared-model combined server (English/Malay + Chughtai) about 1 month ago
Dockerfile

2.39 kB
Drop flash-attn source build (OOM-kills the HF Spaces builder) about 1 month ago
README.md

3.55 kB
docs: add uv setup, .env config, and server/UI run instructions to README 2 months ago
app-2.py

23.8 kB
Deploy: run app_chughtai.py (lexicon) on HF Space; keep app.py/app-2.py about 2 months ago
app.py

17 kB
Serialize all vLLM access with a shared model_lock about 1 month ago
app_chughtai.py

23.3 kB
Serialize all vLLM access with a shared model_lock about 1 month ago
hindi_to_roman_urdu.py

18.2 kB
Initial commit: Qwen3-ASR vLLM server (Chughtai variant), lexicons and project config 2 months ago
main.py

4.42 kB
Split into shared-model combined server (English/Malay + Chughtai) about 1 month ago
requirements.txt

512 Bytes
Initial commit: Qwen3-ASR vLLM server (Chughtai variant), lexicons and project config 2 months ago
shared_model.py

9.56 kB
Serialize all vLLM access with a shared model_lock about 1 month ago