speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

pcm unfix

Browse Source
This commit is contained in:
游雁 2024-11-28 15:53:17 +08:00
parent 345900442d
commit 4b3a28cbc5
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
funasr/utils/load_utils.py
View File

@ -138,7 +138,7 @@ def load_audio_text_image_video(
def load_bytes(input):
input = validate_frame_rate(input)
# input = validate_frame_rate(input)
middle_data = np.frombuffer(input, dtype=np.int16)
middle_data = np.asarray(middle_data)
if middle_data.dtype.kind not in "iu":
@ -153,11 +153,12 @@ def load_bytes(input):
array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
return array
def validate_frame_rate(
input,
fs: int = 16000,
):
# 将文件读取为字节流
byte_data = BytesIO(input)
@ -175,7 +176,7 @@ def validate_frame_rate(
# 获取重新采样后的字节流数据
input = output.read()
return input