fix&feat: 12_SUBTAB.md chỉnh sửa audioclip ở subtab

2026-07-19 08:22:13 +07:00
parent a6ec14b38b
commit d2e0010d88
5 changed files with 3550 additions and 761 deletions
@@ -0,0 +1,87 @@
+import numpy as np
+import scipy.signal as signal
+import librosa
+
+class SubTabDSPEngine:
+    @staticmethod
+    def change_speed(y: np.ndarray, sr: int, speed_ratio: float, preserve_pitch: bool = True) -> np.ndarray:
+        """
+        Alters the playback velocity (Time-Stretching) of a NumPy signal array.
+        """
+        if speed_ratio == 1.0:
+            return y
+            
+        if preserve_pitch:
+            return librosa.effects.time_stretch(y, rate=speed_ratio)
+        else:
+            num_samples_new = int(len(y) / speed_ratio)
+            return signal.resample(y, num_samples_new)
+
+    @staticmethod
+    def normalize(y: np.ndarray, target_db: float = 0.0) -> np.ndarray:
+        """
+        Performs Peak Normalization on an array to scale it to the target decibel value.
+        """
+        target_amplitude = 10.0 ** (target_db / 20.0)
+        max_amplitude = np.max(np.abs(y))
+        
+        if max_amplitude == 0:
+            return y
+            
+        gain = target_amplitude / max_amplitude
+        return y * gain
+
+    @staticmethod
+    def merge_back_to_parent(
+        parent_track_audio: np.ndarray, 
+        sr: int, 
+        edited_sub_audio: np.ndarray, 
+        start_seconds: float, 
+        original_duration_seconds: float
+    ) -> np.ndarray:
+        """
+        Splices the modified audio segment from the Sub-tab back into the parent track array.
+        Applies a 10ms micro-crossfade at the boundaries to eliminate pop/click noise.
+        """
+        start_sample = int(start_seconds * sr)
+        original_samples_len = int(original_duration_seconds * sr)
+        edited_samples_len = len(edited_sub_audio)
+        crossfade_samples = int(0.01 * sr)  # 10ms crossfade window
+        
+        # 1. Allocate the target output array dimension bounds
+        new_total_len = len(parent_track_audio) - original_samples_len + edited_samples_len
+        output_audio = np.zeros(new_total_len, dtype=np.float32)
+        
+        # 2. Extract leading unedited block
+        output_audio[:start_sample] = parent_track_audio[:start_sample]
+        
+        # 3. Stitch the modified audio payload
+        output_audio[start_sample:start_sample + edited_samples_len] = edited_sub_audio
+        
+        # 4. Extract trailing unedited block
+        post_start_original = start_sample + original_samples_len
+        post_start_new = start_sample + edited_samples_len
+        output_audio[post_start_new:] = parent_track_audio[post_start_original:]
+        
+        # 5. Execute micro-crossfade across the initial splice junction
+        if start_sample > crossfade_samples:
+            fade_in_ramp = np.linspace(0.0, 1.0, crossfade_samples)
+            fade_out_ramp = np.linspace(1.0, 0.0, crossfade_samples)
+            
+            # Smooth 10ms interpolation overlay
+            output_audio[start_sample : start_sample + crossfade_samples] = (
+                edited_sub_audio[:crossfade_samples] * fade_in_ramp + 
+                parent_track_audio[start_sample : start_sample + crossfade_samples] * fade_out_ramp
+            )
+            
+        # 6. Execute micro-crossfade across the trailing splice junction
+        if post_start_new + crossfade_samples < len(output_audio):
+            fade_in_ramp = np.linspace(0.0, 1.0, crossfade_samples)
+            fade_out_ramp = np.linspace(1.0, 0.0, crossfade_samples)
+            
+            output_audio[post_start_new : post_start_new + crossfade_samples] = (
+                parent_track_audio[post_start_original : post_start_original + crossfade_samples] * fade_in_ramp +
+                edited_sub_audio[-crossfade_samples:] * fade_out_ramp
+            )
+            
+        return output_audio