Skip to content

fix: int16 overflow in audio scaling and invalid device choice #281

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Bortlesboat wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: int16 overflow in audio scaling and invalid device choice #281

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions demo/vibevoice_asr_gradio_demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,7 @@ def clip_and_encode_audio(
sr = target_sr

# Convert float32 audio to int16 for encoding
segment_data_int16 = (segment_data * 32768.0).astype(np.int16)
segment_data_int16 = (segment_data * 32767.0).astype(np.int16)

# Convert to MP3 if pydub is available and use_mp3 is True
if use_mp3 and HAS_PYDUB:
Expand Down Expand Up @@ -465,7 +465,7 @@ def slice_audio_to_temp(
segment = audio_data[start_idx:end_idx]
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
temp_file.close()
segment_int16 = (segment * 32768.0).astype(np.int16)
segment_int16 = (segment * 32767.0).astype(np.int16)
sf.write(temp_file.name, segment_int16, sample_rate, subtype='PCM_16')
return temp_file.name, None

Expand Down Expand Up @@ -575,7 +575,7 @@ def transcribe_audio(
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
audio_path = temp_file.name
temp_file.close()
audio_data_int16 = (audio_array * 32768.0).astype(np.int16)
audio_data_int16 = (audio_array * 32767.0).astype(np.int16)
sf.write(audio_path, audio_data_int16, sample_rate, subtype='PCM_16')
print(f"[INFO] Microphone audio saved to temp file: {audio_path}")

Expand Down
2 changes: 1 addition & 1 deletion demo/vibevoice_realtime_demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ def main():
p = argparse.ArgumentParser()
p.add_argument("--port", type=int, default=3000)
p.add_argument("--model_path", type=str, default="microsoft/VibeVoice-Realtime-0.5B")
p.add_argument("--device", type=str, default="cuda", choices=["cpu", "cuda", "mpx", "mps"])
p.add_argument("--device", type=str, default="cuda", choices=["cpu", "cuda", "mps"])
p.add_argument("--reload", action="store_true", help="Reload the model or not")
args = p.parse_args()

Expand Down