Last active
April 17, 2025 10:24
-
-
Save istupakov/5ff1a1fa25d575543e8ce98da77bfd63 to your computer and use it in GitHub Desktop.
Read PCM wav file with pure python and numpy
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import wave | |
import numpy as np | |
import numpy.typing as npt | |
def read_wav(filename: str) -> tuple[npt.NDArray[np.float32], int]: | |
""" | |
Read PCM wav file | |
Support PCM_U8, PCM_16, PCM_24 and PCM_32 formats. | |
Parameters: | |
filename : Path to wav file | |
Returns | |
------- | |
waveform : (frames x channels) numpy array with samples [-1, +1] | |
sample_rate : sample rate | |
""" | |
with wave.open(filename, mode="rb") as f: | |
data = f.readframes(f.getnframes()) | |
zero_value = 0 | |
if f.getsampwidth() == 1: | |
buffer = np.frombuffer(data, dtype="u1") | |
zero_value = 1 | |
elif f.getsampwidth() == 3: | |
buffer = np.zeros((len(data) // 3, 4), dtype="V1") | |
buffer[:, -3:] = np.frombuffer(data, dtype="V1").reshape(-1, f.getsampwidth()) | |
buffer = buffer.view(dtype="<i4") | |
else: | |
buffer = np.frombuffer(data, dtype=f"<i{f.getsampwidth()}") | |
max_value = 2 ** (8 * buffer.itemsize - 1) | |
return buffer.reshape(f.getnframes(), f.getnchannels()).astype(np.float32) / max_value - zero_value, f.getframerate() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment