TTS-ORG
/

translation-audio

Automatic Speech Recognition

Model card Files Files and versions

translation-audio / audio

37.1 kB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

mohameddalii's picture

Do not preload cuDNN 12 when running Cohere/PyTorch

7eac989 verified 2 months ago

__init__.py

0 Bytes
Audio translation layer for RTX 5090 / Vast.ai 2 months ago
__main__.py

1.62 kB
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
api.py

4.33 kB
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
app.py

27 Bytes
Audio translation layer for RTX 5090 / Vast.ai 2 months ago
asr.py

6.6 kB
Do not preload cuDNN 12 when running Cohere/PyTorch 2 months ago
cohere_asr.py

7.7 kB
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
compare.py

1.26 kB
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
config.py

925 Bytes
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
cuda_preload.py

1.92 kB
Fix CUDA lib discovery for namespace nvidia package 2 months ago
engine.py

513 Bytes
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
loadtest.py

2.99 kB
Audio translation layer for RTX 5090 / Vast.ai 2 months ago
media.py

1.19 kB
Audio translation layer for RTX 5090 / Vast.ai 2 months ago
metrics.py

1.44 kB
Audio translation layer for RTX 5090 / Vast.ai 2 months ago
pipeline.py

2.97 kB
Add Cohere Transcribe Arabic backend for Whisper vs Cohere compare 2 months ago
queue.py

2.46 kB
Batched Whisper, replica pool for concurrent users, SSE streaming 2 months ago
translation.py

1.14 kB
Audio translation layer for RTX 5090 / Vast.ai 2 months ago