Bug: Error when parsing wav file that ffmpeg understands
Contact Details
What happened?
This problem might be my own fault, because I've written code that converts PCM samples directly to the wav-format that whisper requires, but I am getting the error
/C/Users/USERNAME/AppData/Local/Temp//whisperfile.5925872593102731025: failed to read pcm frames from audio file: At end otalerror: failed to read audio file
when I pass my file to it. Very few of the files my code creates fail. But ffmpeg can convert it, and VLC plays it just fine, so I think there's a non-zero chance it's actually whisperfile's fault?
Anyway, I start whisper in server mode with .\whisperfile-0.9.1.exe --server -m .\whisper\ggml-tiny-q5_1.bin and I send this file to it with curl 127.0.0.1:8080/inference -H "Content-Type: multipart/form-data" -F file="@output-bad.wav" -F temperature="0.0" -F temperature_inc="0.2" -F response_format="json"
Attached is the file that causes this problem. Again, there might be something with my encoder, but other well-known software seems to understand my file just fine and I can't figure out what I'm doing wrong so I figure there's a low chance that I'm actually creating a valid wav.
Version
whisperfile v0.9.1
What operating system are you seeing the problem on?
Windows
Relevant log output
whisper_init_from_file_with_params_no_state: loading model from './whisper/ggml-tiny-q5_1.bin'
whisper_init_with_params_no_state: cuda gpu = 0
whisper_init_with_params_no_state: metal gpu = 0
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 9
whisper_model_load: qntvr = 1
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: CPU total size = 31.57 MB
whisper_model_load: model size = 31.57 MB
whisper_init_state: kv self size = 9.44 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 13.45 MB
whisper_init_state: compute buffer (encode) = 85.79 MB
whisper_init_state: compute buffer (cross) = 4.14 MB
whisper_init_state: compute buffer (decode) = 96.15 MB
whisper server listening at http://127.0.0.1:8080
Received request: output-bad.wav
/C/Users/USERNAME/AppData/Local/Temp//whisperfile.5925872593102731025: failed to read pcm frames from audio file: At end otalerror: failed to read audio fileSource: mozilla-ai/llamafile