From 8a6180e11e0ed6a1374c9ae371619af7befcd1c5 Mon Sep 17 00:00:00 2001
From: yuxumin <1090414006@qq.com>
Date: Sat, 6 Jan 2024 00:03:17 +0800
Subject: [PATCH] add hash code  when naming a se folder

---
 se_extractor.py | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/se_extractor.py b/se_extractor.py
index 3ea2b9d..4727ffe 100644
--- a/se_extractor.py
+++ b/se_extractor.py
@@ -1,6 +1,9 @@
 import os
 import glob
 import torch
+import hashlib
+import librosa
+import base64
 from glob import glob
 import numpy as np
 from pydub import AudioSegment
@@ -10,14 +13,13 @@ from whisper_timestamped.transcribe import get_audio_tensor, get_vad_segments
 model_size = "medium"
 # Run on GPU with FP16
 model = None
-def split_audio_whisper(audio_path, target_dir='processed'):
+def split_audio_whisper(audio_path, audio_name, target_dir='processed', ):
     global model
     if model is None:
         model = WhisperModel(model_size, device="cuda", compute_type="float16")
     audio = AudioSegment.from_file(audio_path)
     max_len = len(audio)
 
-    audio_name = os.path.basename(audio_path).rsplit('.', 1)[0]
     target_folder = os.path.join(target_dir, audio_name)
     
     segments, info = model.transcribe(audio_path, beam_size=5, word_timestamps=True)
@@ -69,7 +71,7 @@ def split_audio_whisper(audio_path, target_dir='processed'):
     return wavs_folder
 
 
-def split_audio_vad(audio_path, target_dir, split_seconds=10.0):
+def split_audio_vad(audio_path, target_dir, audio_name, split_seconds=10.0):
     SAMPLE_RATE = 16000
     audio_vad = get_audio_tensor(audio_path)
     segments = get_vad_segments(
@@ -90,7 +92,6 @@ def split_audio_vad(audio_path, target_dir, split_seconds=10.0):
     
     audio_dur = audio_active.duration_seconds
     print(f'after vad: dur = {audio_dur}')
-    audio_name = os.path.basename(audio_path).rsplit('.', 1)[0]
     target_folder = os.path.join(target_dir, audio_name)
     wavs_folder = os.path.join(target_folder, 'wavs')
     os.makedirs(wavs_folder, exist_ok=True)
@@ -111,14 +112,24 @@ def split_audio_vad(audio_path, target_dir, split_seconds=10.0):
         count += 1
     return wavs_folder
 
+def hash_numpy_array(audio_path):
+    array, _ = librosa.load(audio_path, sr=None)
+    # Convert the array to bytes
+    array_bytes = array.tobytes()
 
-    
+    # Calculate the hash of the array bytes
+    hash_object = hashlib.sha256(array_bytes)
+    hash_value = hash_object.digest()
 
+    # Convert the hash value to base64
+    base64_value = base64.b64encode(hash_value)
+
+    return base64_value.decode('utf-8')[:16].replace('/', '_^')
 
 def get_se(audio_path, vc_model, target_dir='processed', vad=True):
     device = vc_model.device
 
-    audio_name = os.path.basename(audio_path).rsplit('.', 1)[0]
+    audio_name = f"{os.path.basename(audio_path).rsplit('.', 1)[0]}_{hash_numpy_array(audio_path)}"
     se_path = os.path.join(target_dir, audio_name, 'se.pth')
 
     if os.path.isfile(se_path):
@@ -127,9 +138,9 @@ def get_se(audio_path, vc_model, target_dir='processed', vad=True):
     if os.path.isdir(audio_path):
         wavs_folder = audio_path
     elif vad:
-        wavs_folder = split_audio_vad(audio_path, target_dir)
+        wavs_folder = split_audio_vad(audio_path, target_dir=target_dir, audio_name=audio_name)
     else:
-        wavs_folder = split_audio_whisper(audio_path, target_dir)
+        wavs_folder = split_audio_whisper(audio_path, target_dir=target_dir, audio_name=audio_name)
     
     audio_segs = glob(f'{wavs_folder}/*.wav')
     if len(audio_segs) == 0: