mirror of https://github.com/coqui-ai/TTS.git
dbe9cf86ae
in the original implementation, the dataset and model variables were causing errors due to uninitialized in the TTS fairseq models. Changes Made: Introduced a line to split model_name into model_attributes based on the '/' delimiter. This ensures that the different components of the model name (language, dataset, model) can be separately and accurately accessed. Added lines to explicitly extract lang, dataset, and model from model_attributes using their respective indices. This change makes the code more robust and clear, as it directly links the variables to their sources: lang is now set to the second component (model_attributes[1]), dataset to the third (model_attributes[2]), model to the fourth (model_attributes[3]). |
||
|---|---|---|
| .. | ||
| audio | ||
| __init__.py | ||
| callbacks.py | ||
| capacitron_optimizer.py | ||
| distribute.py | ||
| download.py | ||
| downloaders.py | ||
| generic_utils.py | ||
| io.py | ||
| manage.py | ||
| radam.py | ||
| samplers.py | ||
| synthesizer.py | ||
| training.py | ||
| vad.py | ||