bhetherman 263f39e0a3 Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support ...

Upgrade PyTorch to 2.7+ with cu128 wheels for Blackwell (sm_120) GPU
support. Replace silero-vad (which depends on torchaudio) with a direct
ONNX Runtime implementation of the same Silero VAD model, eliminating
the torchaudio dependency entirely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-08 04:01:27 -04:00

reference_audio

initial commit

2026-04-07 03:58:35 -04:00

server

Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support

2026-04-08 04:01:27 -04:00

static

initial commit

2026-04-07 03:58:35 -04:00

.dockerignore

updates for docker take 1

2026-04-08 03:05:26 -04:00

.gitignore

updates for docker take 1

2026-04-08 03:05:26 -04:00

.gitmodules

updates for docker take 1

2026-04-08 03:05:26 -04:00

docker-compose.yml

updates for docker take 1

2026-04-08 03:05:26 -04:00

Dockerfile

Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support

2026-04-08 04:01:27 -04:00

requirements.txt

Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support

2026-04-08 04:01:27 -04:00

run.py

initial commit

2026-04-07 03:58:35 -04:00

S

Description

No description provided

525 KiB

Languages

Python 64.7%

JavaScript 23.1%

CSS 6.4%

HTML 3%

Dockerfile 2.8%