Comments (2)
actually, checking the folders, it seems like the models weren't stored where they're supposed to be. Instead, they were only stored in hf cache folder
I found the fix only for the download. It requires the new huggingface_hub version with the updated download workflow introduced in version 0.23.0. only problem left is that it doesn't seem to load the model.
Python 3.10.9
Launching transcription engine
py app valid: true
DEBUG::operator ():: config_path: Resources/app_config.yml
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
Input Device id 0 - Microsoft Sound Mapper - Input
Input Device id 1 - Microphone (Razer Seiren Mini)
Input Device id 2 - Headset Microphone (Oculus Virt
Input Device id 3 - Microphone (2- VR P10 Dongle)
Input Device id 4 - Microphone (WO Mic Device)
Input Device id 5 - Microphone (Virtual Desktop Aud
Input Device id 6 - Microphone (Steam Streaming Mic
Input Device id 7 - CABLE Output (VB-Audio Virtual
Finding mic 1
Mic 1 requested, treating it as a numerical device ID
Found mic 1: Microphone (Razer Seiren Mini)
Mic sample rate: 44100
Model yumfood/whisper_distil_medium_en_ct2 will be saved to C:\Users\*****\Downloads\TaSTT\Resources\Models\yumfood/whisper_distil_medium_en_ct2
Traceback (most recent call last):
File "C:\Users\*****\Downloads\TaSTT\Resources\Scripts\transcribe_v2.py", line 1270, in <module>
run(cfg)
File "C:\Users\*****\Downloads\TaSTT\Resources\Scripts\transcribe_v2.py", line 1185, in run
whisper = Whisper(collector, cfg)
File "C:\Users\*****\Downloads\TaSTT\Resources\Scripts\transcribe_v2.py", line 435, in __init__
self.model = WhisperModel(model_str,
File "C:\Users\*****\Downloads\TaSTT\Resources\Python\lib\site-packages\faster_whisper\transcribe.py", line 114, in __init__
model_path = download_model(
File "C:\Users\*****\Downloads\TaSTT\Resources\Python\lib\site-packages\faster_whisper\utils.py", line 58, in download_model
raise ValueError(
ValueError: Invalid model size 'yumfood/whisper_distil_medium_en_ct2', expected one of: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2
Command exited with code 1: 0: The operation completed successfully.
from tastt.
Complete fix for it was to upgrade to the latest versions of huggingface_hub and faster-whisper.
The way I was able to fix it manually was by going into TaSTT\Resources\Python and running the following command:
python -m pip install huggingface_hub faster-whisper --upgrade
The only problem being that the ct2 medium distil model don't seem too reliable and it doesn't show download progress.
from tastt.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tastt.