zsh: exec format error: ./whisper-tiny.en.llamafile
#4
by
dollarpound
- opened
Unable to execute in Ubuntu 22
DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=22.04
DISTRIB_CODENAME=jammy
DISTRIB_DESCRIPTION="Ubuntu 22.04.4 LTS"
If you use zsh and have trouble running llamafile, try saying sh -c ./llamafile. This is due to a bug that was fixed in zsh 5.9+.
https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#mac
jartine
changed discussion status to
closed
The executable worked, but inference failed.
Server log
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: CPU total size = 77.11 MB
whisper_model_load: model size = 77.11 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: audio.mp3
ID3: converting to wav...
ID3: failed to open audio file: Resource does not exist (we support .wav, .mp3, .flac, and .ogg)
error: failed to read WAV file
Inference
~/Desktop/yt
➜ curl 127.0.0.1:8080/inference \
-H "Content-Type: multipart/form-data" \
-F file="@./audio.mp3" \
-F temperature="0.0" \
-F temperature_inc="0.2" \
-F response_format="json"
{"error":"failed to read WAV file"}%
~/Desktop/yt
➜ lll
total 84M
-rw-rw-r-- 1 glasscube 2.6M Aug 29 23:44 vercel.m4a
-rw-rw-r-- 1 glasscube 74M Aug 29 23:45 output.wav
-rw-rw-r-- 1 glasscube 6.8M Aug 29 23:47 audio.mp3
drwxr-xr-x 4 glasscube 4.0K Aug 29 23:50 ../
drwxrwxr-x 2 glasscube 4.0K Aug 29 23:47 ./
~/Desktop/yt
@jartine any help?
No support in server for mp3s yet. You have to convert to s16 wav or use the cli.