Missing file
- Dominant language
- Jupyter Notebook
- Stars
- 434
- Forks
- 84
- PR merge metrics
- No merged PRs in 30d
Description
Hello Mustafa & Ziad,
I have checked your awesome work, which is really helpful to me, but I have a question please ,,I am new to this field, so could you please share with me a good reference to understand the difference between hifi-GAN and Mel-GAN?, I have checked a lot of references over the internet, but they were not that helpful!
Also I have another question related to the vocoder and speaker used, when I tried different combinations I have listened and was able to know that the vocoder HiFi-GAN and the speaker universal is the best combination,,but when I tried combination LJSpeech & HIFI-GAN , I received error that the file generator_LJSpeech.pth.tar does not exist, and when I checked the files and the code, I can see the code points to this directoryFastSpeech2/hifigan/generator_LJSpeech.pth.tar but , this file does not exist "generator_LJSpeech.pth.tar"
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by inspecting the FastSpeech2/hifigan/ path and the code reference to generator_LJSpeech.pth.tar. Check which model files are present and determine whether the missing artifact or its referenced location is expected; done means the LJSpeech and HiFi-GAN combination no longer fails with a missing-file error.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100