Fixed: `--realign` "UnicodeDecodeError" error. Fixed: `--realign` error if there is more than one line per sub. Fixed: `--realign` "File not found" error. Fixed: ImportError: libctranslate2-d3638643.so.4.4.0 [Linux] Fixed: ffmpeg: error while loading shared libraries [Linux] Hide: "not compiled with flash attention" warning. Fixed: "cuda:1" didn't work with MDX [untested, "r245.3" fix was broken] New VAD models: `silero_v6_fw`, `silero_v6` [patched], `nemo_v2`, `ten` [its threshold is offset by +0.2] Change: `--vad_method` default is set to `ten` Change: Batched mode has few improvements Change: `--compute_type` defaults to `default` if CUDA, else `auto`. Updated: torch to 2.8.0+cu128 [to support 50xx GPUs on torch models] Updated: onnxruntime_gpu to 1.21.1 [cuDNN 9.x] Updated: pyinstaller to 6.16.0 [Faster-Whisper-XXL Pro](https://github.com/Purfview/whisper-standalone-win/discussions/456)

Experimental tests. Read and write there ->https://github.com/Purfview/whisper-standalone-win/issues/224

Experimental tests.

Faster Whisper implementation using optimized CTranslate2 models. GPU execution requires [cuBLAS and cuDNN libs](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Last included commit: #145: https://github.com/guillaumekln/faster-whisper/commit/1562b02345c8587eff1c6694b28c7f91f5c20ec2 ## Some new stuff: * Includes "Ignore repeated prompt" [PR #163]

Faster Whisper implementation using optimized CTranslate2 models. GPU execution requires [cuBLAS and cuDNN libs](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Last included commit: #145: https://github.com/guillaumekln/faster-whisper/commit/1562b02345c8587eff1c6694b28c7f91f5c20ec2 ## Some new stuff: * New argument: `repetition_penalty`

Faster Whisper implementation using optimized CTranslate2 models. GPU execution requires [cuBLAS and cuDNN libs](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Last included commit: #143: https://github.com/guillaumekln/faster-whisper/commit/857be6f621c4b940cf784925cd2c94e40d16235f # Some new stuff: * New argument: `prompt_reset_on_temperature`

Faster Whisper implementation using optimized CTranslate2 models. GPU execution requires [cuBLAS and cuDNN libs](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Last included commit: #141: https://github.com/guillaumekln/faster-whisper/commit/5c17de17713f65929c7c33add3a9735ff75a945c

Faster Whisper implementation using optimized CTranslate2 models. GPU execution requires [cuBLAS and cuDNN libs](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Last included commit: #141: https://github.com/guillaumekln/faster-whisper/commit/5c17de17713f65929c7c33add3a9735ff75a945c ## Some new stuff: * New argument: `--skip`. (read there: https://github.com/Purfview/whisper-standalone-win/discussions/47)