feat: add conversion audio data flow img

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.wav filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -8,43 +8,43 @@ print("os.path.dirname:", os.path.dirname(os.path.abspath(__file__)))
 # Define the audio file paths (replace with your actual paths)
 audio_files = {
     "EN": {
-        "source1": os.path.join(curr_dir,"asset/audio/speech_clone_samples/source/-8014568635405176842.wav"),
-        "source2": os.path.join(curr_dir,"asset/audio/speech_clone_samples/source/2188769758301752050.wav"),
+        "source1": os.path.join(curr_dir, "asset/audio/speech_clone_samples/source/-8014568635405176842.wav"),
+        "source2": os.path.join(curr_dir, "asset/audio/speech_clone_samples/source/2188769758301752050.wav"),
         "prompt1": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt1/4813840990459345930.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt1/-4261051484297537007.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt1/4813840990459345930.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt1/-4261051484297537007.wav")
         ],
         "prompt2": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt2/-5427774732334682307.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt2/-8434461861028245286.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt2/-5427774732334682307.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt2/-8434461861028245286.wav")
         ],
         "gen1": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen1/5518114099457736437.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen1/7702800575106132714.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen1/5518114099457736437.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen1/7702800575106132714.wav")
         ],
         "gen2": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen2/-3552571881595006474.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen2/1663763965594639195.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen2/-3552571881595006474.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen2/1663763965594639195.wav")
         ]
     },
     "ZH": {
-        "source1": os.path.join(curr_dir,"asset/audio/speech_clone_samples/source/6180100163014579264.wav"),
-        "source2": os.path.join(curr_dir,"asset/audio/speech_clone_samples/source/3454520432972073544.wav"),
+        "source1": os.path.join(curr_dir, "asset/audio/speech_clone_samples/source/6180100163014579264.wav"),
+        "source2": os.path.join(curr_dir, "asset/audio/speech_clone_samples/source/3454520432972073544.wav"),
         "prompt3": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt3/-3133904573328901327.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt3/-6807997165982172717.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt3/-3133904573328901327.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt3/-6807997165982172717.wav")
         ],
         "prompt4": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt4/3957690686751537502.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/prompt/prompt4/-6025252638827969073.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt4/3957690686751537502.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/prompt/prompt4/-6025252638827969073.wav")
         ],
         "gen3": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen3/4648220778277450149.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen3/3417274376341807017.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen3/4648220778277450149.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen3/3417274376341807017.wav")
         ],
         "gen4": [
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen4/8580165735770550130.wav"),
-            os.path.join(curr_dir,"asset/audio/speech_clone_samples/generated/gen4/-2291633937079669023.wav")
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen4/8580165735770550130.wav"),
+            os.path.join(curr_dir, "asset/audio/speech_clone_samples/generated/gen4/-2291633937079669023.wav")
         ]
     }
 }
@@ -52,8 +52,8 @@ audio_files = {
 
 def create_audio_demo():
     with gr.Blocks(title="Voice Conversion") as demo:
+        gr.Image(os.path.join(curr_dir, "asset/img/converted_audio.png"), height=120)
         gr.Markdown("# Voice Conversion")
-
         with gr.Tabs():
             with gr.TabItem("English (EN)"):
                 with gr.Row():