语音转录失败，卡在6%

[wky199702]

问题描述 | Problem Description

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\videoCaptioner\VideoCaptioner\app\core\thread\transcript_thread.py", line 130, in run
asr_data = self.asr.run(callback=self.progress_callback)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\videoCaptioner\VideoCaptioner\app\core\bk_asr\BaseASR.py", line 73, in run
resp_data = self._run(callback, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\videoCaptioner\VideoCaptioner\app\core\bk_asr\WhisperASR.py", line 145, in _run
raise RuntimeError(f"生成 SRT 文件失败: {str(e)}")
RuntimeError: 生成 SRT 文件失败: WhisperCPP 执行失败: Using GPU "NVIDIA GeForce RTX 4070", feature level 12.1, effective flags Wave32 | NoReshapedMatMul
Loaded MEL filters, 62.8 kb RAM
Loaded vocabulary, 51865 strings, 3037.1 kb RAM
Loaded 1259 GPU tensors, 2950.66 MB VRAM
Computed CPU base frequency: 3.4944 GHz
Loaded model from "F:\videoCaptioner\VideoCaptioner\AppData\models\ggml-large-v2.bin" to VRAM
Created source reader from the file "C:\Users\Administrator\AppData\Local\Temp\bk_asr\tmpu2qmtl4b\audio.wav"
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past
last text repeated, clearing token/prompt past

日志信息（可选）| Logs (Optional)

[philpw99]

WhisperCPP 确实很有问题，我30分钟的视频也卡在28%不动了。