Title: Best-quality settings for faster-whisper-xxl.exe (speed not important) #540

Hi! I’m using faster-whisper-xxl.exe and I want maximum transcription/subtitle quality (I don’t care about speed).

This is my current command:

$env:CUDA_VISIBLE_DEVICES="0"
chcp 65001 > $null

$purfExe="faster-whisper-xxl.exe"

& $purfExe -d cuda
-l en -m large-v2
--compute_type float16 --beam_size 7
--best_of 1 --temperature 0
--temperature_increment_on_fallback 0.2 --output_format srt
--standard --batched --batch_size 6
--beep_off -o=source
"D:\Videos\myvideo.mp4"

For best accuracy, should I switch to -m large-v3 (if supported) and/or --compute_type float32?

What are the recommended values for --beam_size, --best_of, --temperature, and --temperature_increment_on_fallback when optimizing for quality?

Are there any other flags (e.g., VAD options, punctuation/diarization options, etc.) that improve subtitle quality in this build?

Does --batched affect accuracy, or only speed/VRAM?

Environment (if useful):

OS: Windows
rtx 4070

Device: CUDA GPU (can provide GPU model/VRAM if needed)

Output: .srt

Thanks!