How to use to transcribe specific audio files

[Soeroah]

Hi,

I'm pretty unskilled at python so I usually need help with command lines.

I've got some short, 1-4 minute files I'd like to get transcribed and this project was recommended. However, each time I run the command I get a progress bar showing 1.5 gigabytes of data being processed, when the total size of the files in the folder I want transcribed are sub-100 megabytes.

I'm pretty sure the program is just grabbing audio files from somewhere on my PC but I have no idea where. How do I customise which files specifically I want to have transcribed?

Thank you.

[glangford]

You can change to the directory of your audio files using the cd command. Then run whisper. Or you can specify the path to your files, as suggested here

• Error opening input files: No such file or directory #2091 (comment)

If you have a number of files of the same type (eg. .wav or .mp3) you can just list them one by one on the command line, or you can process all the files of one type like this

whisper *.mp3 --language en --verbose True --output_format txt

To see the different options, use

whisper --help

[glangford]

This warning is saying that whisper is downloading the model used to transcribe the speech.

See these past discussions to try and troubleshoot the checksum error

• Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model. #1027
• Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model. #1218

[Soeroah]

Thank you. I let it run to completion and it seems to be working, though it takes a little while for transcription to start.

I think I've got the hang of it now

[Soeroah]

Actually, sorry to reopen - I've tried running the "do all files of this type" as you suggested above but I get the following error

C:\Users\David\Documents\SoundRecordMp3\SoundRecordMp3\bin\Debug\Output>
C:\Users\David\Documents\SoundRecordMp3\SoundRecordMp3\bin\Debug\Output>whisper .mp3 --language en --verbose True --output_format txt --output_dir "C:\Users\David\Documents\SoundRecordMp3\SoundRecordMp3\bin\Debug\Output"
C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper_init_.py:150: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(fp, map_location=device)
C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\transcribe.py:126: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Traceback (most recent call last):
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\audio.py", line 58, in load_audio
out = run(cmd, capture_output=True, check=True).stdout
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 571, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ffmpeg', '-nostdin', '-threads', '0', '-i', '.mp3', '-f', 's16le', '-ac', '1', '-acodec', 'pcm_s16le', '-ar', '16000', '-']' returned non-zero exit status 4294967274.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\transcribe.py", line 597, in cli
result = transcribe(model, audio_path, temperature=temperature, **args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\transcribe.py", line 133, in transcribe
mel = log_mel_spectrogram(audio, model.dims.n_mels, padding=N_SAMPLES)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\audio.py", line 140, in log_mel_spectrogram
audio = load_audio(audio)
^^^^^^^^^^^^^^^^^
File "C:\Users\David\AppData\Local\Programs\Python\Python311\Lib\site-packages\whisper\audio.py", line 60, in load_audio
raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 2024-07-24-git-896c22ef00-full_build-www.gyan.dev Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 13.2.0 (Rev5, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 28.100 / 59. 28.100
libavcodec 61. 10.100 / 61. 10.100
libavformat 61. 5.101 / 61. 5.101
libavdevice 61. 2.100 / 61. 2.100
libavfilter 10. 2.102 / 10. 2.102
libswscale 8. 2.100 / 8. 2.100
libswresample 5. 2.100 / 5. 2.100
libpostproc 58. 2.100 / 58. 2.100
[in#0 @ 00000213e1a72ac0] Error opening input: Invalid argument
Error opening input file *.mp3.
Error opening input files: Invalid argument

Skipping *.mp3 due to RuntimeError: Failed to load audio: ffmpeg version 2024-07-24-git-896c22ef00-full_build-www.gyan.dev Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 13.2.0 (Rev5, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 28.100 / 59. 28.100
libavcodec 61. 10.100 / 61. 10.100
libavformat 61. 5.101 / 61. 5.101
libavdevice 61. 2.100 / 61. 2.100
libavfilter 10. 2.102 / 10. 2.102
libswscale 8. 2.100 / 8. 2.100
libswresample 5. 2.100 / 5. 2.100
libpostproc 58. 2.100 / 58. 2.100
[in#0 @ 00000213e1a72ac0] Error opening input: Invalid argument
Error opening input file *.mp3.
Error opening input files: Invalid argument

I think if I do it one by one with a full filepath in the line it works, but for some reason doing all at once doesn't?

[glangford]

Ah...I see you are on Windows, and it doesn't like '*' to wildcard, which is the standard way to do this on other platforms. My mistake.

Error opening input file *.mp3.
Error opening input files: Invalid argument

See here for more information

Is there any way to get the windows cmd shell to expand wildcard paths

• https://superuser.com/questions/460598/is-there-any-way-to-get-the-windows-cmd-shell-to-expand-wildcard-paths?rq=1

[Soeroah]

Ah, damn, powershell.. I've got no idea how to modify the whisper command to work with that

I'll look into it but if anyone happens to know the answer I'll be looking for I'd appreciate the help. Like I said, I'm a pretty basic non-programmer user

Edit: For anyone in the future looking, I found one that works for batching with windows called Faster-Whisper-XXL