cociweb / custom_whisper Goto Github PK

Used docker-compose and logs are attached.

• ha_net is defined elsewhere.
• in the computer I have 2 nVidia GPU.

whisper_log.txt
docker_compose.txt

It turned out that the github action building process uses a wrong upstream image version from dockerhub's python repository.
The result will be that the base image will be identical as amd64.

I try to install it in a fresh HA x86 install, but:

s6-rc: info: service s6rc-oneshot-runner: starting
s6-rc: info: service s6rc-oneshot-runner successfully started
s6-rc: info: service fix-attrs: starting
s6-rc: info: service fix-attrs successfully started
s6-rc: info: service legacy-cont-init: starting
s6-rc: info: service legacy-cont-init successfully started
s6-rc: info: service whisper: starting
s6-rc: info: service whisper successfully started
s6-rc: info: service discovery: starting
INFO:main:Downloading custom model Small to /data
INFO:wyoming_faster_whisper.download:model.bin is downloaded into /data/custom from url: https://huggingface.co/Hungarians/Whisper-small-hu-cleaned/resolve/main/fp32/model.bin
INFO:wyoming_faster_whisper.download:vocabulary.txt is downloaded into /data/custom from url: https://huggingface.co/Hungarians/Whisper-small-hu-cleaned/resolve/main/fp32/vocabulary.txt
INFO:wyoming_faster_whisper.download:config.json is downloaded into /data/custom from url: https://huggingface.co/Hungarians/Whisper-small-hu-cleaned/resolve/main/fp32/config.json
INFO:wyoming_faster_whisper.download:hash.json is downloaded into /data/custom from url: https://huggingface.co/Hungarians/Whisper-small-hu-cleaned/resolve/main/fp32/hash.json
INFO:main:Succesfully downloaded the custom model: custom
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "/usr/local/lib/python3.11/dist-packages/wyoming_faster_whisper/main.py", line 182, in
asyncio.run(main())
File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/wyoming_faster_whisper/main.py", line 141, in main
AsrModel(
TypeError: AsrModel.init() missing 1 required positional argument: 'version'
[11:48:24] INFO: Service exited with code 1 (by signal 0)
INFO:main:Downloading custom model Small to /data

Download loop contiue forever...

I've converted custom model myself and put it to "custom" folder. But container always tries to download it. If I dont specify web address of the model it shows the following error:
TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'
And it also deletes my data!

Actually I don't see any improvement against the original faster-widget container TBH, exept new directory "custom".

Is it possible just to start a container with my local custom model that I already have on my server?

Greetings!

I hope this message finds you well. I'm reaching out from Argentina, currently attempting to load a Spanish model into Whisper. I've successfully installed custom_whisper in Docker using the suggested docker-compose.yml, and everything is running smoothly. However, when I try to load a model.bin from another Spanish model, I encounter the following error:

RuntimeError: Unsupported model binary version. This executable supports models with binary version v6 or below, but the model has binary version v1868833084. This usually means that the model was generated by a later version of CTranslate2. (Forward compatibility is not guaranteed.)

I've tested several models, all yielding the same result. Are there any Spanish models compatible with this setup? I'm pleased with how easy it was to set up, but the Hungarian language isn't suitable for my needs.

Thank you for your assistance!