Duplicate from manavisrani07/gradio-lipsync-wav2lip

Co-authored-by: Manav Israni <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+images/comparison.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,16 @@
+---
+title: Gradio Lipsync Wav2lip
+emoji: 👄
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+python_version: 3.8
+sdk_version: 3.40.1
+suggested_hardware: t4-medium
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: manavisrani07/gradio-lipsync-wav2lip
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import subprocess
+from subprocess import call
+
+with gr.Blocks() as ui:
+    with gr.Row():
+        video = gr.File(label="Video or Image", info="Filepath of video/image that contains faces to use")
+        audio = gr.File(label="Audio", info="Filepath of video/audio file to use as raw audio source")
+        with gr.Column():
+            checkpoint = gr.Radio(["wav2lip", "wav2lip_gan"], label="Checkpoint", info="Name of saved checkpoint to load weights from")
+            no_smooth = gr.Checkbox(label="No Smooth", info="Prevent smoothing face detections over a short temporal window")
+            resize_factor = gr.Slider(minimum=1, maximum=4, step=1, label="Resize Factor", info="Reduce the resolution by this factor. Sometimes, best results are obtained at 480p or 720p")
+    with gr.Row():
+        with gr.Column():
+            pad_top = gr.Slider(minimum=0, maximum=50, step=1, value=0, label="Pad Top", info="Padding above")
+            pad_bottom = gr.Slider(minimum=0, maximum=50, step=1, value=10, label="Pad Bottom (Often increasing this to 20 allows chin to be included)", info="Padding below lips")
+            pad_left = gr.Slider(minimum=0, maximum=50, step=1, value=0, label="Pad Left", info="Padding to the left of lips")
+            pad_right = gr.Slider(minimum=0, maximum=50, step=1, value=0, label="Pad Right", info="Padding to the right of lips")
+            generate_btn = gr.Button("Generate")
+        with gr.Column():
+           result = gr.Video()
+
+    def generate(video, audio, checkpoint, no_smooth, resize_factor, pad_top, pad_bottom, pad_left, pad_right):
+        if video is None or audio is None or checkpoint is None:
+            return
+        
+        smooth = "--nosmooth" if no_smooth else ""
+        
+        
+        cmd = [
+            "python",
+            "inference.py",
+            "--checkpoint_path", f"checkpoints/{checkpoint}.pth",
+            "--segmentation_path", "checkpoints/face_segmentation.pth",
+            "--enhance_face", "gfpgan",
+            "--face", video.name,
+            "--audio", audio.name,
+            "--outfile", "results/output.mp4",
+        ]
+
+        call(cmd)
+        return "results/output.mp4"
+
+    generate_btn.click(
+        generate, 
+        [video, audio, checkpoint, pad_top, pad_bottom, pad_left, pad_right, resize_factor], 
+        result)
+    
+ui.queue().launch(debug=True)

audio.py

@@ -0,0 +1,142 @@
+import librosa
+import librosa.filters
+import numpy as np
+# import tensorflow as tf
+from scipy import signal
+from scipy.io import wavfile
+from hparams import hparams as hp
+
+def load_wav(path, sr):
+    return librosa.core.load(path, sr=sr)[0]
+
+def save_wav(wav, path, sr):
+    wav *= 32767 / max(0.01, np.max(np.abs(wav)))
+    #proposed by @dsmiller
+    wavfile.write(path, sr, wav.astype(np.int16))
+
+def save_wavenet_wav(wav, path, sr):
+    librosa.output.write_wav(path, wav, sr=sr)
+
+def preemphasis(wav, k, preemphasize=True):
+    if preemphasize:
+        return signal.lfilter([1, -k], [1], wav)
+    return wav
+
+def inv_preemphasis(wav, k, inv_preemphasize=True):
+    if inv_preemphasize:
+        return signal.lfilter([1], [1, -k], wav)
+    return wav
+
+def get_hop_size():
+    hop_size = hp.hop_size
+    if hop_size is None:
+        assert hp.frame_shift_ms is not None
+        hop_size = int(hp.frame_shift_ms / 1000 * hp.sample_rate)
+    return hop_size
+
+def linearspectrogram(wav):
+    D = _stft(preemphasis(wav, hp.preemphasis, hp.preemphasize))
+    S = _amp_to_db(np.abs(D)) - hp.ref_level_db
+    
+    if hp.signal_normalization:
+        return _normalize(S)
+    return S
+
+def melspectrogram(wav):
+    D = _stft(preemphasis(wav, hp.preemphasis, hp.preemphasize))
+    S = _amp_to_db(_linear_to_mel(np.abs(D))) - hp.ref_level_db
+    
+    if hp.signal_normalization:
+        return _normalize(S)
+    return S
+
+def _lws_processor():
+    import lws
+    return lws.lws(hp.n_fft, get_hop_size(), fftsize=hp.win_size, mode="speech")
+
+def _stft(y):
+    if hp.use_lws:
+        return _lws_processor(hp).stft(y).T
+    else:
+        return librosa.stft(y=y, n_fft=hp.n_fft, hop_length=get_hop_size(), win_length=hp.win_size)
+
+##########################################################
+#Those are only correct when using lws!!! (This was messing with Wavenet quality for a long time!)
+def num_frames(length, fsize, fshift):
+    """Compute number of time frames of spectrogram
+    """
+    pad = (fsize - fshift)
+    if length % fshift == 0:
+        M = (length + pad * 2 - fsize) // fshift + 1
+    else:
+        M = (length + pad * 2 - fsize) // fshift + 2
+    return M
+
+
+def pad_lr(x, fsize, fshift):
+    """Compute left and right padding
+    """
+    M = num_frames(len(x), fsize, fshift)
+    pad = (fsize - fshift)
+    T = len(x) + 2 * pad
+    r = (M - 1) * fshift + fsize - T
+    return pad, pad + r
+##########################################################
+#Librosa correct padding
+def librosa_pad_lr(x, fsize, fshift):
+    return 0, (x.shape[0] // fshift + 1) * fshift - x.shape[0]
+
+# Conversions
+_mel_basis = None
+
+def _linear_to_mel(spectogram):
+    global _mel_basis
+    if _mel_basis is None:
+        _mel_basis = _build_mel_basis()
+    return np.dot(_mel_basis, spectogram)
+
+def _build_mel_basis():
+    assert hp.fmax <= hp.sample_rate // 2
+    return librosa.filters.mel(
+        sr=hp.sample_rate,
+        n_fft=hp.n_fft,
+        n_mels=hp.num_mels,
+        fmin=hp.fmin,
+        fmax=hp.fmax
+    )
+
+def _amp_to_db(x):
+    min_level = np.exp(hp.min_level_db / 20 * np.log(10))
+    return 20 * np.log10(np.maximum(min_level, x))
+
+def _db_to_amp(x):
+    return np.power(10.0, (x) * 0.05)
+
+
+def _normalize(S):
+    if hp.allow_clipping_in_normalization:
+        if hp.symmetric_mels:
+            return np.clip((2 * hp.max_abs_value) * ((S - hp.min_level_db) / (-hp.min_level_db)) - hp.max_abs_value,
+                           -hp.max_abs_value, hp.max_abs_value)
+        else:
+            return np.clip(hp.max_abs_value * ((S - hp.min_level_db) / (-hp.min_level_db)), 0, hp.max_abs_value)
+    
+    assert S.max() <= 0 and S.min() - hp.min_level_db >= 0
+    if hp.symmetric_mels:
+        return (2 * hp.max_abs_value) * ((S - hp.min_level_db) / (-hp.min_level_db)) - hp.max_abs_value
+    else:
+        return hp.max_abs_value * ((S - hp.min_level_db) / (-hp.min_level_db))
+
+def _denormalize(D):
+    if hp.allow_clipping_in_normalization:
+        if hp.symmetric_mels:
+            return (((np.clip(D, -hp.max_abs_value,
+                              hp.max_abs_value) + hp.max_abs_value) * -hp.min_level_db / (2 * hp.max_abs_value))
+                    + hp.min_level_db)
+        else:
+            return ((np.clip(D, 0, hp.max_abs_value) * -hp.min_level_db / hp.max_abs_value) + hp.min_level_db)
+    
+    if hp.symmetric_mels:
+        return (((D + hp.max_abs_value) * -hp.min_level_db / (2 * hp.max_abs_value)) + hp.min_level_db)
+    else:
+        return ((D * -hp.min_level_db / hp.max_abs_value) + hp.min_level_db)

basicsr/__init__.py

@@ -0,0 +1,12 @@
+# https://github.com/xinntao/BasicSR
+# flake8: noqa
+from .archs import *
+from .data import *
+from .losses import *
+from .metrics import *
+from .models import *
+from .ops import *
+from .test import *
+from .train import *
+from .utils import *
+#from .version import __gitsha__, __version__

basicsr/apply_sr.py

@@ -0,0 +1,25 @@
+import cv2
+import numpy as np
+import torch
+
+from basicsr.archs.rrdbnet_arch import RRDBNet
+
+
+def init_sr_model(model_path):
+    model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32)
+    model.load_state_dict(torch.load(model_path)['params'], strict=True)
+    model.eval()
+    model = model.cuda()
+    return model
+
+
+def enhance(model, image):
+    img = image.astype(np.float32) / 255.
+    img = torch.from_numpy(np.transpose(img[:, :, [2, 1, 0]], (2, 0, 1))).float()
+    img = img.unsqueeze(0).cuda()
+    with torch.no_grad():
+        output = model(img)
+    output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
+    output = np.transpose(output[[2, 1, 0], :, :], (1, 2, 0))
+    output = (output * 255.0).round().astype(np.uint8)
+    return output

basicsr/archs/__init__.py

@@ -0,0 +1,25 @@
+import importlib
+from copy import deepcopy
+from os import path as osp
+
+from basicsr.utils import get_root_logger, scandir
+from basicsr.utils.registry import ARCH_REGISTRY
+
+__all__ = ['build_network']
+
+# automatically scan and import arch modules for registry
+# scan all the files under the 'archs' folder and collect files ending with
+# '_arch.py'
+arch_folder = osp.dirname(osp.abspath(__file__))
+arch_filenames = [osp.splitext(osp.basename(v))[0] for v in scandir(arch_folder) if v.endswith('_arch.py')]
+# import all the arch modules
+_arch_modules = [importlib.import_module(f'basicsr.archs.{file_name}') for file_name in arch_filenames]
+
+
+def build_network(opt):
+    opt = deepcopy(opt)
+    network_type = opt.pop('type')
+    net = ARCH_REGISTRY.get(network_type)(**opt)
+    logger = get_root_logger()
+    logger.info(f'Network [{net.__class__.__name__}] is created.')
+    return net