File size: 1,261 Bytes
8ad2ab3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
import whisper
from .compute_vps_score import compute_vps_score # Ensure this path is correct
def main():
# 🔧 Set your input audio file path here
audio_path = r"D:\Intern\shankh\audio_samples\obama_short.wav"
# 🔧 Choose Whisper model (tiny, base, small, medium, large)
model_size = "base"
print(f"Loading Whisper model: {model_size}")
whisper_model = whisper.load_model(model_size)
print(f"Analyzing audio: {audio_path}")
try:
vps_result = compute_vps_score(audio_path, whisper_model)
print("\n--- Voice Pacing Score (VPS) ---")
print(f"VPS Score: {vps_result['VPS']:.2f}")
print(f" - SRS (Speech Rate Stability): {vps_result['SRS']:.2f}")
print(f" - PAS (Pause Appropriateness): {vps_result['PAS']:.2f}")
print(f" - NPP: {vps_result['NPP']:.2f}")
print(f" - AFW: {vps_result['AFW']:.2f}")
print(f" - RCS (Rhythm Consistency): {vps_result['RCS']:.2f}")
print(f" - STR: {vps_result['STR']:.2f}")
print(f" - STW: {vps_result['STW']:.2f}")
print("\nTranscript:")
print(vps_result["transcript"])
except Exception as e:
print(f"[Error] {e}")
if __name__ == "__main__":
main()
|