Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-24 06:26:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 76db75f5b51b5d066ce7d010701769ea49b555e4 into c0d2f624c09dc18e709e37c2ad90c039a4eb72a2

Browse Source
This commit is contained in:
Raivis Dejus 2025-06-27 02:27:58 +00:00 committed by GitHub
commit c626f6e49c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
whisper/audio.py
View File

@ -51,15 +51,16 @@ def load_audio(file: str, sr: int = SAMPLE_RATE):
"-ac", "1", "-ac", "1",
"-acodec", "pcm_s16le", "-acodec", "pcm_s16le",
"-ar", str(sr), "-ar", str(sr),
"-loglevel", "error",
"-" "-"
] ]
# fmt: on # fmt: on
try: result = run(cmd, capture_output=True)
out = run(cmd, capture_output=True, check=True).stdout
except CalledProcessError as e:
raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0 if len(result.stderr):
raise RuntimeError(f"Failed to load audio: {result.stderr.decode()}")
return np.frombuffer(result.stdout, np.int16).flatten().astype(np.float32) / 32768.0
def pad_or_trim(array, length: int = N_SAMPLES, *, axis: int = -1): def pad_or_trim(array, length: int = N_SAMPLES, *, axis: int = -1):