m-bain / whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
BSD 2-Clause "Simplified" License
11.24k stars 1.18k forks source link

ROCM support for AMD GPUs #566

Open TheMaddax opened 10 months ago

TheMaddax commented 10 months ago

I've been using whisper with my AMD 6600 XT, which functioned well with ROCM support. However, with whisperx, it seems like it is not supported to use AMD GPUs. Is there any chance for ROCM support to be implemented with whisperx?

kandeshvari commented 8 months ago

As I understand the reason is in the ctranslate2 package. There is an issue with AMD support but with no progress :( https://github.com/OpenNMT/CTranslate2/issues/1072

radna0 commented 2 months ago

Any update on this?

arlo-phoenix commented 1 month ago

@radna0 You can test my CTranslate2 ROCm fork. See https://github.com/OpenNMT/CTranslate2/issues/1072#issuecomment-2271843277. Works very well on my RX6800 GPU and should probably work on every AMD GPU that supports ROCm.