Ma/auto-caption
1
0
Fork 0
mirror of https://github.com/HiMeditator/auto-caption.git synced 2026-02-13 02:54:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(engine): 字幕引擎启动路径适配、音频重采样函数适配

Browse Source
This commit is contained in:
himeditator mac
2025-07-30 00:16:54 +08:00
parent 1b7ff33656
commit a7a60da260
5 changed files with 13 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
engine/utils/audioprcs.py
View File

@@ -39,15 +39,15 @@ def resample_chunk_mono(chunk: bytes, channels: int, orig_sr: int, target_sr: in
单通道音频数据块
"""
if channels == 1:
chunk_mono = chunk
chunk_mono = np.frombuffer(chunk, dtype=np.int16)
chunk_mono = chunk_mono.astype(np.float32)
else:
# (length * channels,)
chunk_np = np.frombuffer(chunk, dtype=np.int16)
# (length, channels)
chunk_np = chunk_np.reshape(-1, channels)
# (length,)
chunk_mono_f = np.mean(chunk_np.astype(np.float32), axis=1)
chunk_mono = chunk_mono_f.astype(np.int16)
chunk_mono = np.mean(chunk_np.astype(np.float32), axis=1)
ratio = target_sr / orig_sr
chunk_mono_r = samplerate.resample(chunk_mono, ratio, converter_type=mode)
@@ -69,6 +69,7 @@ def resample_mono_chunk(chunk: bytes, orig_sr: int, target_sr: int, mode="sinc_b
单通道音频数据块
"""
chunk_np = np.frombuffer(chunk, dtype=np.int16)
chunk_np = chunk_np.astype(np.float32)
ratio = target_sr / orig_sr
chunk_r = samplerate.resample(chunk_np, ratio, converter_type=mode)
chunk_r = np.round(chunk_r).astype(np.int16)