Tasha Upchurch
d9170f804b
Key updates: Added AddFramesToVideoFolder node to add frames to a video folder Introduced VideoFolderProvider and VideoDefinitionProvider nodes to manage video folders and video definitions Added FadeToInVideoFolder node for fading between frames in a video folder Implemented ListedSVDConditioning node for applying SVD conditioning to a list of parameters Added VideoFolderFFMPEGVideoInterpolate node to interpolate frames in a video folder using FFmpeg Introduced AudioFolderProvider and AudioDefinitionProvider nodes for managing audio folders and definitions Added AddAudioToAudioFolder and AddSilenceToAudioFolder nodes for adding audio files and silence to audio folders Implemented GetAudioFilesLengthsFromAudioFolder node to retrieve lengths of audio files in a folder Added AudioFolderRenderAudio node to join audio files in an audio folder Introduced GenerateMusic node for generating music from descriptions using the AudioCraft library Added XttsNode for text-to-speech conversion using the XTTS library Implemented AdjustAudioVolumeForFiles node to adjust volume for a list of audio files The changes also include the addition of LiteLLM nodes for text generation: Added FuncAnysToText node that runs Python code with multiple input types and outputs a string Introduced FuncAnysToLatent node for running code that outputs a latent representation Added FuncAnysToString node for executing code with various inputs and producing a string output Implemented FuncAnysToList node to run code that takes different input types and returns a list Added FuncAnysToCond node for running code with multiple inputs and generating a conditioning output These new nodes expand the capabilities for video and audio processing, allowing more advanced manipulations and generation of video and audio content within the graph.
94 lines
2.5 KiB
Python
94 lines
2.5 KiB
Python
import argparse
|
|
import torch.multiprocessing as mp
|
|
|
|
from concurrent.futures import ProcessPoolExecutor, as_completed
|
|
|
|
def generate_xtts_for_text(text, file, lang, speaker):
|
|
from TTS.api import TTS
|
|
import torch
|
|
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
|
|
tts.tts_to_file(
|
|
text=text,
|
|
speaker_wav=speaker,
|
|
language=lang,
|
|
file_path=file,
|
|
# emotion="angry", # doesnt do anything as far as i can tell with xtts2
|
|
)
|
|
|
|
|
|
def generate_xtts(**kwargs):
|
|
import torch
|
|
import ast
|
|
import uuid
|
|
from concurrent.futures import ProcessPoolExecutor, as_completed
|
|
|
|
torch.cuda.empty_cache()
|
|
|
|
text = kwargs.get('text')
|
|
folder = kwargs.get('folder', '.')
|
|
lang = kwargs.get('lang', 'en')
|
|
speaker = kwargs.get('speaker', '')
|
|
|
|
try:
|
|
texts = ast.literal_eval(text)
|
|
except SyntaxError:
|
|
texts = [text]
|
|
|
|
o_files = []
|
|
batch_size = 3
|
|
with ProcessPoolExecutor(max_workers=batch_size) as executor:
|
|
futures = []
|
|
for i, text in enumerate(texts):
|
|
ii = str(i).zfill(1 + len(str(1 + len(texts))))
|
|
file_to_use = f"{folder}/tts_{ii}_{str(uuid.uuid4())}.wav"
|
|
future = executor.submit(generate_xtts_for_text, text, file_to_use, lang, speaker)
|
|
futures.append((future, file_to_use))
|
|
|
|
for future, file_to_use in futures:
|
|
future.result()
|
|
o_files.append(file_to_use)
|
|
|
|
torch.cuda.empty_cache()
|
|
|
|
return (o_files[0], o_files,)
|
|
|
|
|
|
|
|
|
|
# def generate_xtts_for_text_advanced(text, file, lang, speaker):
|
|
# from TTS.api import TTS
|
|
# import torch
|
|
#
|
|
# # Create a SharedMemoryManager
|
|
# manager = mp.Manager()
|
|
# # Create a shared list to store the result
|
|
# result = manager.list()
|
|
# model = manager.model()
|
|
#
|
|
#
|
|
# # also we want to SHARE the TTS model
|
|
# something = manager.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description='Generate from given text.')
|
|
parser.add_argument('--text', help='Text to generate for')
|
|
parser.add_argument('--folder', type=str, default='.', help='output folder')
|
|
parser.add_argument('--lang', type=str, default='en')
|
|
parser.add_argument('--speaker', type=str, default='', help='Speaker wav use for generation')
|
|
|
|
args = parser.parse_args()
|
|
kwargs = vars(args)
|
|
|
|
print(f"Generating with the following arguments: {kwargs}")
|
|
generated_files = generate_xtts(**kwargs)
|
|
print(f"Generated files: {generated_files}")
|
|
|
|
if __name__ == "__main__":
|
|
main() |