-
I've fine-tuned the **llama 3 8 billion** model. I followed the notebook and only changed the dataset. The dataset is similar to the **alpaca dataset** but for the **Bangla language**. I've trained th…
-
Hi,
Really love the work done in this repo, it has been really helpful. Just a request, could you please add more documentation regarding fine-tuning the models for a new voice, using available mode…
-
**Can anyone help me please**
(venv) C:\Users\Dragn\Documents\WeeaBlind-master\WeeaBlind-master\venv>python weeablind.py
C:\Users\Dragn\Documents\WeeaBlind-master\WeeaBlind-master\venv\output\sa…
-
### Describe the bug
` error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
[end of out…
li589 updated
1 month ago
-
### Describe the bug
Try to run the command `pip install --upgrade tts` and got a error
### Is there an existing issue for this?
- [x] I have searched the existing issues
### Reproduction
…
-
Hi, thanks for the finetuned models!
Could you share your code for model loading and python env details?
The inference example posted in the readme is giving me a weights mismatch error.
```s…
-
### Describe the bug
I'm getting `ModuleNotFoundError: No module named 'bangla'` when trying to use `from TTS.api import TTS`, before actually trying to do anything with the library.
### To Repr…
-
I am trying to use TrOCR for recognizing Urdu text from image. For feature extractor, I am using DeiT and bert-base-multilingual-cased as decoder. I can't figure out what will be the requirements if I…
-
I was trying to use your whisper training pipeline but the following error occurred.
`RuntimeError: The size of tensor a (500) must match the size of tensor b (448) at non-singleton dimension 1`
…
-
Some weights of the model checkpoint at sagorsarker/bangla-bert-base were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight'…