- Fix race condition: pass return_timestamps as parameter instead of mutating shared state - Remove /local/transcriptions endpoint (path traversal vulnerability) - Add timeout=30 and URL scheme validation to prevent SSRF - Add temp file cleanup via try/finally in all route handlers - AsyncTaskManager: add threading.Lock and TTL cleanup for completed tasks - Change audio_rate to 16000 (matches Whisper's expected sample rate) - Extract filename from URL via Content-Disposition/path - Detect base64 audio format via python-magic - Fix response_size_bytes to use json.dumps instead of str() - Move scipy import to module level - Clamp temperature to [0.0, 1.0] - Deduplicate _load_model() code - Fix docstrings, README structure, typo, log level Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
20 lines
1.6 KiB
Plaintext
20 lines
1.6 KiB
Plaintext
# Conda environment dependencies
|
|
|
|
# Torch
|
|
torch @ https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-manylinux_2_28_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.13'
|
|
torch @ https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp312-cp312-manylinux_2_28_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'
|
|
torch @ https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp311-cp311-manylinux_2_28_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'
|
|
|
|
# Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
|
|
flash_attn @ https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.13'
|
|
flash_attn @ https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'
|
|
flash_attn @ https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'
|
|
|
|
Flask==3.1.0
|
|
flask-cors==4.0.0
|
|
waitress==3.0.0
|
|
scipy==1.13.1
|
|
transformers==4.49.0
|
|
accelerate==1.4.0
|
|
python-magic==0.4.27
|