theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update audio.py (#1349)

Browse Source
This commit is contained in:
Zhongjie Duan
2026-03-13 17:57:14 +08:00
committed by GitHub
parent 8c9ddc9274
commit 7650e9381e
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
diffsynth/utils/data/audio.py
View File

@@ -1,7 +1,5 @@
import torch import torch
import torchaudio import torchaudio
from torchcodec.decoders import AudioDecoder
from torchcodec.encoders import AudioEncoder
def convert_to_mono(audio_tensor: torch.Tensor) -> torch.Tensor: def convert_to_mono(audio_tensor: torch.Tensor) -> torch.Tensor:
@@ -47,6 +45,7 @@ def read_audio_with_torchcodec(
tuple[torch.Tensor, int]: A tuple containing the audio tensor and the sample rate. tuple[torch.Tensor, int]: A tuple containing the audio tensor and the sample rate.
The audio tensor shape is [C, T] where C is the number of channels and T is the number of audio frames. The audio tensor shape is [C, T] where C is the number of channels and T is the number of audio frames.
""" """
from torchcodec.decoders import AudioDecoder
decoder = AudioDecoder(path) decoder = AudioDecoder(path)
stop_seconds = None if duration is None else start_time + duration stop_seconds = None if duration is None else start_time + duration
waveform = decoder.get_samples_played_in_range(start_seconds=start_time, stop_seconds=stop_seconds).data waveform = decoder.get_samples_played_in_range(start_seconds=start_time, stop_seconds=stop_seconds).data
@@ -102,6 +101,7 @@ def save_audio(waveform: torch.Tensor, sample_rate: int, save_path: str, backend
waveform = waveform[0] waveform = waveform[0]
if backend == "torchcodec": if backend == "torchcodec":
from torchcodec.encoders import AudioEncoder
encoder = AudioEncoder(waveform, sample_rate=sample_rate) encoder = AudioEncoder(waveform, sample_rate=sample_rate)
encoder.to_file(dest=save_path) encoder.to_file(dest=save_path)
else: else: