projecte-aina

/

tts-ca-coqui-vits-multispeaker

like 4

Hello

Two quick comments:

1. On the sample there are these imports:

import tempfile
import gradio as gr
import numpy as np
import os
import json

I do not think that they are needed. There is no need to install all these dependencies (e..g gradio).

2. When trying to load the model, following the receipe in the README.md, Coqui gives the error bellow.

When I try to look at the contents of the config.json I cannot see a plain text file, instead "archive/data.pklFBZZZZZZZZZZZZZ"

May be I should load the model following a specifc instructions? Or may the model is published in an incorrect format? I do not know.

Code used:

def syntetize():
from typing import Optional
from TTS.config import load_config
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer

model_path = "aina/model/best_model.pth"
config_path = "aina/model/config.json"
speakers_file_path = "aina/model/speakers.pth"

text = "Hola amics!"
speaker_idx = "1"

synthesizer = Synthesizer(
model_path, config_path, speakers_file_path, None, None, None,
)
wavs = synthesizer.tts(text, speaker_idx)

Thanks

Jordi

File "/home/jordi/sc/aina-python/lib/python3.11/site-packages/TTS/config/init.py", line 89, in load_config
data = json.load(f)
^^^^^^^^^^^^
File "/usr/lib/python3.11/json/init.py", line 293, in load
return loads(fp.read(),
^^^^^^^^^
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte