Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,959 Bytes
cb12676 631258d cb12676 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
import torch
import os
from concurrent.futures import ThreadPoolExecutor
from pydub import AudioSegment
import cv2
from pathlib import Path
import subprocess
from pathlib import Path
import av
import imageio
import numpy as np
from rich.progress import track
from tqdm import tqdm
import stf_alternative
def exec_cmd(cmd):
subprocess.run(
cmd, shell=True, check=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT
)
def images2video(images, wfp, **kwargs):
fps = kwargs.get("fps", 24)
video_format = kwargs.get("format", "mp4") # default is mp4 format
codec = kwargs.get("codec", "libx264") # default is libx264 encoding
quality = kwargs.get("quality") # video quality
pixelformat = kwargs.get("pixelformat", "yuv420p") # video pixel format
image_mode = kwargs.get("image_mode", "rgb")
macro_block_size = kwargs.get("macro_block_size", 2)
ffmpeg_params = ["-crf", str(kwargs.get("crf", 18))]
writer = imageio.get_writer(
wfp,
fps=fps,
format=video_format,
codec=codec,
quality=quality,
ffmpeg_params=ffmpeg_params,
pixelformat=pixelformat,
macro_block_size=macro_block_size,
)
n = len(images)
for i in track(range(n), description="writing", transient=True):
if image_mode.lower() == "bgr":
writer.append_data(images[i][..., ::-1])
else:
writer.append_data(images[i])
writer.close()
# print(f':smiley: Dump to {wfp}\n', style="bold green")
print(f"Dump to {wfp}\n")
def merge_audio_video(video_fp, audio_fp, wfp):
if osp.exists(video_fp) and osp.exists(audio_fp):
cmd = f"ffmpeg -i {video_fp} -i {audio_fp} -c:v copy -c:a aac {wfp} -y"
exec_cmd(cmd)
print(f"merge {video_fp} and {audio_fp} to {wfp}")
else:
print(f"video_fp: {video_fp} or audio_fp: {audio_fp} not exists!")
class STFPipeline:
def __init__(self,
stf_path: str = "/home/user/app/stf/",
device: str = "cuda:0",
template_video_path: str = "templates/front_one_piece_dress_nodded_cut.webm",
config_path: str = "front_config.json",
checkpoint_path: str = "089.pth",
root_path: str = "works"
):
config_path = os.path.join(stf_path, config_path)
checkpoint_path = os.path.join(stf_path, checkpoint_path)
work_root_path = os.path.join(stf_path, root_path)
model = stf_alternative.create_model(
config_path=config_path,
checkpoint_path=checkpoint_path,
work_root_path=work_root_path,
device=device,
wavlm_path="microsoft/wavlm-large",
)
self.template = stf_alternative.Template(
model=model,
config_path=config_path,
template_video_path=template_video_path,
)
def execute(self, audio: str):
Path("dubbing").mkdir(exist_ok=True)
save_path = os.path.join("dubbing", Path(audio).stem+"--lip.mp4")
reader = iter(self.template._get_reader(num_skip_frames=0))
audio_segment = AudioSegment.from_file(audio)
pivot = 0
results = []
with ThreadPoolExecutor(4) as p:
try:
gen_infer = self.template.gen_infer_concurrent(
p,
audio_segment,
pivot,
)
for idx, (it, chunk) in enumerate(gen_infer, pivot):
frame = next(reader)
composed = self.template.compose(idx, frame, it)
frame_name = f"{idx}".zfill(5)+".jpg"
results.append(it['pred'])
pivot = idx + 1
except StopIteration as e:
pass
images2video(results, save_path)
return save_path |