Sharrnah

thanks. but still no luck. I placed the spkrec-ecapa-voxceleb stuff besides the pipeline config and changed the config accordingly: ```yaml pipeline: name: pyannote.audio.pipelines.SpeakerDiarization params: clustering: AgglomerativeClustering embedding: speechbrain/spkrec-ecapa-voxceleb embedding_batch_size: 32...

except that this is exactly what i tried some time ago without success. Would have to try it again to see if it works now or if i was just...

i think something that confirms my guess. In Italian, if you add a `.` (dot) at the end of a sentence, it very often speaks that dot "punkto". it should...

i think this is fixed. :) Never had any issues again. (sorry. forgot about this)

Same issue here. Compared it with the official whisper implementation. - Official whisper does not increase VRAM over time. - Faster Whisper increases VRAM usage over time without releasing it....

If i understand it correctly, he is just removing the models from memory and reloading it. Thats not really a solution but a workaround as that introduces a huge delay...

I see the same issue when i set a language. (medium and large-v3 model tested). Happens on medium.en just as on other models if a language is set. If i...

As update: It was introduced with this commit: https://github.com/SYSTRAN/faster-whisper/commit/092067208b45e5eb935bfe8b0ac42b8341da9434 When i revert this one back, its fine again.

> @Sharrnah , hello. Can you try again with this [fix](https://github.com/SYSTRAN/faster-whisper/pull/705) ? Thanks. looks fine with the fix. :)

But it's a lot more than double the used memory as mentioned in #3401