Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-11-04 14:16:57 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

add multitalk support for audio in mp4

Browse Source
This commit is contained in:
DeepBeepMeep 2025-09-04 01:25:19 +02:00
parent e5abb1b9bc
commit 56a51b79f0
1 changed files with 24 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
models/wan/multitalk/multitalk.py
View File

@ -60,6 +60,29 @@ def get_embedding(speech_array, wav2vec_feature_extractor, audio_encoder, sr=160
audio_emb = audio_emb.cpu().detach() audio_emb = audio_emb.cpu().detach()
return audio_emb return audio_emb
def extract_audio_from_video(filename, sample_rate):
raw_audio_path = filename.split('/')[-1].split('.')[0]+'.wav'
ffmpeg_command = [
"ffmpeg",
"-y",
"-i",
str(filename),
"-vn",
"-acodec",
"pcm_s16le",
"-ar",
"16000",
"-ac",
"2",
str(raw_audio_path),
]
subprocess.run(ffmpeg_command, check=True)
human_speech_array, sr = librosa.load(raw_audio_path, sr=sample_rate)
human_speech_array = loudness_norm(human_speech_array, sr)
os.remove(raw_audio_path)
return human_speech_array
def audio_prepare_single(audio_path, sample_rate=16000, duration = 0): def audio_prepare_single(audio_path, sample_rate=16000, duration = 0):
ext = os.path.splitext(audio_path)[1].lower() ext = os.path.splitext(audio_path)[1].lower()
if ext in ['.mp4', '.mov', '.avi', '.mkv']: if ext in ['.mp4', '.mov', '.avi', '.mkv']: