Pull Text from .TXT file using Colab

[FrankLidgad]

In Colab can you add the code to a cell to pull the Text from a .TXT file as opposed to copying and pasting ?

This is available in the installed PC method but not in the Colab.

Thank you.

PS: Are there any 'Voice' repositories available other than what is in the Colab? (.WAV)

[SummerChild90]

Cell 1

`!pip3 install -U scipy

!git clone https://github.com/jnordberg/tortoise-tts.git
%cd tortoise-tts
!pip3 install transformers==4.19.0
!pip3 install -r requirements.txt
!python3 setup.py install

import torch
import torchaudio
import torch.nn as nn
import torch.nn.functional as F

import IPython

from tortoise.api import TextToSpeech
from tortoise.utils.audio import load_audio, load_voice, load_voices

tts = TextToSpeech()

import os
from google.colab import files`

Cell 2

`# upload at least 2 audio clips. They must be a WAV file, 6-10 seconds long.
CUSTOM_VOICE_NAME = "custom"

custom_voice_folder = f"tortoise/voices/{CUSTOM_VOICE_NAME}"
os.makedirs(custom_voice_folder)
for i, file_data in enumerate(files.upload().values()):
with open(os.path.join(custom_voice_folder, f'{i}.wav'), 'wb') as f:
f.write(file_data)`

Cell 3

uploaded = files.upload()
for file_name, file_data in uploaded.items():
text = file_data.decode('utf-8')

Break text into chunks of 100 characters

text_chunks = [text[i:i+100] for i in range(0, len(text), 100)]

Pick a "preset mode" to determine quality. Options: {"ultra_fast", "fast" (default), "standard", "high_quality"}. See docs in api.py

preset = "high_quality"

Generate speech for each chunk of text

for i, chunk in enumerate(text_chunks):
gen = tts.tts_with_preset(chunk, voice_samples=voice_samples, conditioning_latents=conditioning_latents,
preset=preset)
torchaudio.save(f'generated-{CUSTOM_VOICE_NAME}-{i}.wav', gen.squeeze(0).cpu(), 24000)

Combine all generated speech files into a single file

combined = []
for i in range(len(text_chunks)):
file_path = f'generated-{CUSTOM_VOICE_NAME}-{i}.wav'
combined.append(load_audio(file_path))
combined = torch.cat(combined, dim=1)

Save and play the combined speech file

torchaudio.save(f'generated-{CUSTOM_VOICE_NAME}.wav', combined, 24000)
IPython.display.Audio(f'generated-{CUSTOM_VOICE_NAME}.wav')