Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import parselmouth | |
| from parselmouth.praat import call | |
| import numpy as np | |
| import pandas as pd | |
| def find_rises_and_peaks_gradient(data, threshold=4): | |
| data['rise_point'] = 0 | |
| data['peak_point'] = 0 | |
| pitch_values = data['pitch'].values | |
| gradients = np.gradient(pitch_values) | |
| in_rise = False | |
| rise_start = 0 | |
| successive_rise_count = 0 | |
| min_successive_rise = 3 # Minimum successive values to qualify as a rise | |
| checking_rise = False # Flag to start checking for rises after NaN | |
| for i in range(1, len(gradients)): | |
| if np.isnan(pitch_values[i]): | |
| checking_rise = False # Reset flag when encountering NaN | |
| in_rise = False | |
| successive_rise_count = 0 | |
| continue | |
| if not checking_rise: | |
| checking_rise = True # Start checking for rises after NaN | |
| continue | |
| if gradients[i] >= threshold: | |
| if not in_rise: | |
| in_rise = True | |
| rise_start = i-1 | |
| successive_rise_count += 1 | |
| else: | |
| if in_rise: | |
| if successive_rise_count >= min_successive_rise: | |
| data.at[rise_start, 'rise_point'] = 1 | |
| data.at[i-1, 'peak_point'] = 1 | |
| in_rise = False | |
| successive_rise_count = 0 | |
| return data | |
| def get_pitch(audio_data): | |
| rate, data = audio_data | |
| if data.ndim > 1: # Check if the audio is stereo or multi-channel | |
| data = np.mean(data, axis=1) # Convert to mono by averaging channels | |
| # Convert data to float64 for compatibility with Parselmouth | |
| data = data.astype('float64') | |
| sound = parselmouth.Sound(values=data, sampling_frequency=rate) | |
| try: | |
| pitch = call(sound, "To Pitch", 0.0, 75, 500) | |
| pitch_values = pitch.selected_array['frequency'] | |
| # return "Pitch frequencies: " + str(pitch_values) | |
| pitch_values[pitch_values==0] = np.nan | |
| df_pitch = pd.DataFrame(np.column_stack([pitch.xs(), pitch_values]), | |
| columns=['time', 'pitch']) | |
| df_pitch = find_rises_and_peaks_gradient(df_pitch) | |
| output = df_pitch.to_json(orient='records') | |
| return output | |
| except Exception as e: | |
| return "Error in pitch extraction: " + str(e) | |
| demo = gr.Interface(fn=get_pitch, inputs="audio", outputs="text") | |
| demo.launch() | |