问题描述 | Problem Description
Faster Whisper 错误，这是为什么。使用的是联想拯救者Y9000P 2025 RTX 5060 Laptop
日志信息（可选）| Logs (Optional)
……
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
ISFT : Lavf60.16.100
Chapters:
Chapter #0:0: start 0.000000, end 3824.085000
Metadata:
title :
Stream #0:0(und): Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s (default)
Metadata:
handler_name : Sound Media Handler
vendor_id : [0][0][0][0]
encoder : Lavc60.31.102 pcm_s16le
size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x
size= 14080kB time=00:07:30.69 bitrate= 255.9kbits/s speed= 901x
size= 27392kB time=00:14:43.57 bitrate= 254.0kbits/s speed= 883x
size= 41216kB time=00:21:59.88 bitrate= 255.8kbits/s speed= 880x
size= 54784kB time=00:29:17.72 bitrate= 255.3kbits/s speed= 879x
size= 68608kB time=00:36:37.10 bitrate= 255.8kbits/s speed= 879x
size= 82176kB time=00:43:57.32 bitrate= 255.3kbits/s speed= 879x
size= 96000kB time=00:51:17.44 bitrate= 255.5kbits/s speed= 879x
size= 109824kB time=00:58:38.81 bitrate= 255.7kbits/s speed= 880x
[out#0/wav @ 000001cf879f0940] video:0kB audio:119501kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.000064%
size= 119501kB time=01:03:44.02 bitrate= 256.0kbits/s speed= 881x
开始语音转录
Faster Whisper 执行命令: faster-whisper-xxl.exe -m lv3-turbo-japanese --print_progress -l ja --model_dir D:\software\VideoCaptionerV3.7.0\VideoCaptioner\_internal\AppData\models C:\Users\DUHAIH~1\AppData\Local\Temp\bk_asr\tmp6dwz4sbi\audio.wav -d cuda --output_format srt --multilingual true --japanese kanji -o source --vad_filter true --vad_threshold 0.40 --vad_method silero_v3 --one_word 0 --sentence --max_line_width 100 --max_line_count 1 --max_comma 20 --max_comma_cent 50 --repetition_penalty 1.00 --beep_off
Standalone Faster-Whisper-XXL r245.4 running on: CUDA
Starting to process: C:\Users\DUHAIH~1\AppData\Local\Temp\bk_asr\tmp6dwz4sbi\audio.wav
Starting sequential faster-whisper inference.
Traceback (most recent call last):
File "D:\whisper-fast-XXL\__main__.py", line 2324, in <module>
File "D:\whisper-fast-XXL\__main__.py", line 2191, in cli
File "faster_whisper\transcribe.py", line 2179, in restore_speech_timestamps
File "faster_whisper\transcribe.py", line 1471, in generate_segments
File "faster_whisper\transcribe.py", line 1719, in encode
RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED
[PYI-26964:ERROR] Failed to execute script '__main__' due to unhandled exception!
Faster Whisper 返回值: 1
2026-06-29 12:44:56 - faster_whisper - ERROR - Faster Whisper 错误:
2026-06-29 12:44:56 - transcript_thread - ERROR - 转录过程中发生错误:
Traceback (most recent call last):
File "app\core\thread\transcript_thread.py", line 212, in run
File "app\core\bk_asr\BaseASR.py", line 73, in run
File "app\core\bk_asr\FasterWhisperASR.py", line 267, in _run
RuntimeError
问题描述 | Problem Description
Faster Whisper 错误，这是为什么。使用的是联想拯救者Y9000P 2025 RTX 5060 Laptop
日志信息（可选）| Logs (Optional)