Switch to librosa pitch_shift + custom formant shift (no parselmouth dependency)

app_simple.py

@@ -1,21 +1,20 @@
 #!/usr/bin/env python3
-"""Simple Elderly Voice Converter using pitch/formant shifting (librosa + parselmouth)."""
+"""Simple Elderly Voice Converter using librosa for pitch shift + simple formant shift."""
 import os
 import tempfile
 import gradio as gr
 import numpy as np
 import soundfile as sf
 import librosa
-import parselmouth
-from parselmouth.praat import call
+import librosa.effects
 
 TITLE = "🎭 Elderly Voice Converter (Pitch + Formant Shift)"
 DESCRIPTION = """
 基于 **音调偏移 + 共振峰偏移** 的轻量级声音转换，模拟老年人声线特征。
 
 **原理：**
-- **降低基频 (Pitch)**：老年人声带松弛，基频更低
-- **降低共振峰**：声道变长/肌肉松弛，共振峰下移
+- **降低基频 (Pitch)**：使用 librosa PSOLA 算法降低音调
+- **降低共振峰**：通过频谱包络偏移模拟声道变长
 - **添加气声**：模拟声带闭合不全的气息感
 
 **使用方法：**
@@ -48,39 +47,78 @@ def convert_voice_simple(
     # Load audio
     y, sr = librosa.load(input_audio_path, sr=None, mono=True)
     
-    # Convert to parselmouth Sound
-    sound = parselmouth.Sound(y, sampling_frequency=sr)
-    
-    # 1. Pitch shift using PSOLA (Change pitch command)
+    # 1. Pitch shift using librosa's PSOLA (reliable)
     if pitch_shift != 0:
-        pitch_ratio = 2 ** (pitch_shift / 12.0)
-        # Change pitch: pitch_ratio, time_step, min_pitch, max_pitch
-        sound = call(sound, "Change pitch", pitch_ratio, 0.01, 50, 500)
+        y = librosa.effects.pitch_shift(y, sr=sr, n_steps=pitch_shift)
     
-    # 2. Formant shift (Change formants command)
+    # 2. Formant shift via spectral envelope manipulation
     if formant_shift != 0:
-        formant_ratio = 2 ** (formant_shift / 12.0)
-        # Change formants: formant_ratio, new_pitch_median
-        sound = call(sound, "Change formants", formant_ratio, 1.0)
+        y = shift_formants(y, sr, formant_shift)
     
-    # 3. Add breathiness (mix with noise)
+    # 3. Add breathiness
     if breathiness > 0:
-        noise = np.random.normal(0, breathiness * 0.1, len(sound.values[0]))
-        sound.values[0] = sound.values[0] * (1 - breathiness) + noise * breathiness
-    
-    # Get result
-    result_audio = sound.values[0].astype(np.float32)
-    result_sr = sound.sampling_frequency
+        noise = np.random.normal(0, breathiness * 0.1 * np.std(y), len(y))
+        y = y * (1 - breathiness) + noise * breathiness
     
-    # Resample if needed
-    if result_sr != sr:
-        result_audio = librosa.resample(result_audio, orig_sr=result_sr, target_sr=sr)
+    # Normalize to prevent clipping
+    y = y / (np.max(np.abs(y)) + 1e-6) * 0.95
     
     # Save
-    sf.write(output_audio_path, result_audio, sr, subtype='PCM_16')
+    sf.write(output_audio_path, y, sr, subtype='PCM_16')
     return output_audio_path
 
 
+def shift_formants(y, sr, formant_shift_semitones):
+    """
+    Shift formants by manipulating spectral envelope.
+    Positive = higher formants, Negative = lower formants.
+    """
+    if formant_shift_semitones == 0:
+        return y
+    
+    # Convert semitones to frequency ratio
+    ratio = 2 ** (formant_shift_semitones / 12.0)
+    
+    # STFT
+    n_fft = 2048
+    hop_length = 512
+    stft = librosa.stft(y, n_fft=n_fft, hop_length=hop_length)
+    magnitude = np.abs(stft)
+    phase = np.angle(stft)
+    
+    # Shift spectral envelope along frequency axis
+    # Simple approach: interpolate magnitude spectrum
+    n_freqs = magnitude.shape[0]
+    new_freqs = np.linspace(0, n_freqs - 1, int(n_freqs / ratio))
+    
+    if ratio < 1:  # Lower formants (stretch)
+        # Interpolate to expand
+        from scipy.interpolate import interp1d
+        interp_func = interp1d(np.arange(n_freqs), magnitude, axis=0, kind='linear', fill_value='extrapolate')
+        magnitude = interp_func(new_freqs)
+        # Truncate or pad to original size
+        if magnitude.shape[0] > n_freqs:
+            magnitude = magnitude[:n_freqs]
+        else:
+            pad = np.zeros((n_freqs - magnitude.shape[0], magnitude.shape[1]))
+            magnitude = np.vstack([magnitude, pad])
+    else:  # Higher formants (compress)
+        from scipy.interpolate import interp1d
+        interp_func = interp1d(np.arange(n_freqs), magnitude, axis=0, kind='linear', fill_value='extrapolate')
+        magnitude = interp_func(new_freqs)
+        if magnitude.shape[0] < n_freqs:
+            pad = np.zeros((n_freqs - magnitude.shape[0], magnitude.shape[1]))
+            magnitude = np.vstack([magnitude, pad])
+        else:
+            magnitude = magnitude[:n_freqs]
+    
+    # Reconstruct
+    stft_new = magnitude * np.exp(1j * phase)
+    y_new = librosa.istft(stft_new, hop_length=hop_length, length=len(y))
+    
+    return y_new
+
+
 def process_audio(
     audio_file,
     pitch_shift,
@@ -104,6 +142,7 @@ def process_audio(
         
         return output_path, "✅ 转换完成！"
     except Exception as e:
+        import traceback
         return None, f"❌ 转换失败: {str(e)}"