feat: add audio converted demo

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip 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

app.py

@@ -0,0 +1,116 @@
+import gradio as gr
+
+# Define the audio file paths (replace with your actual paths)
+audio_files = {
+    "EN": {
+        "source1": "asset/audio/speech_clone_samples/source/-8014568635405176842.wav",
+        "source2": "asset/audio/speech_clone_samples/source/2188769758301752050.wav",
+        "prompt1": [
+            "asset/audio/speech_clone_samples/prompt/prompt1/4813840990459345930.wav",
+            "asset/audio/speech_clone_samples/prompt/prompt1/-4261051484297537007.wav"
+        ],
+        "prompt2": [
+            "asset/audio/speech_clone_samples/prompt/prompt2/-5427774732334682307.wav",
+            "asset/audio/speech_clone_samples/prompt/prompt2/-8434461861028245286.wav"
+        ],
+        "gen1": [
+            "asset/audio/speech_clone_samples/generated/gen1/5518114099457736437.wav",
+            "asset/audio/speech_clone_samples/generated/gen1/7702800575106132714.wav"
+        ],
+        "gen2": [
+            "asset/audio/speech_clone_samples/generated/gen2/-3552571881595006474.wav",
+            "asset/audio/speech_clone_samples/generated/gen2/1663763965594639195.wav"
+        ]
+    },
+    "ZH": {
+        "source1": "asset/audio/speech_clone_samples/source/6180100163014579264.wav",
+        "source2": "asset/audio/speech_clone_samples/source/3454520432972073544.wav",
+        "prompt3": [
+            "asset/audio/speech_clone_samples/prompt/prompt3/-3133904573328901327.wav",
+            "asset/audio/speech_clone_samples/prompt/prompt3/-6807997165982172717.wav"
+        ],
+        "prompt4": [
+            "asset/audio/speech_clone_samples/prompt/prompt4/3957690686751537502.wav",
+            "asset/audio/speech_clone_samples/prompt/prompt4/-6025252638827969073.wav"
+        ],
+        "gen3": [
+            "asset/audio/speech_clone_samples/generated/gen3/4648220778277450149.wav",
+            "asset/audio/speech_clone_samples/generated/gen3/3417274376341807017.wav"
+        ],
+        "gen4": [
+            "asset/audio/speech_clone_samples/generated/gen4/8580165735770550130.wav",
+            "asset/audio/speech_clone_samples/generated/gen4/-2291633937079669023.wav"
+        ]
+    }
+}
+
+
+def create_audio_demo():
+    with gr.Blocks(title="Voice Conversion") as demo:
+        gr.Markdown("# Voice Conversion")
+
+        with gr.Tabs():
+            with gr.TabItem("English (EN)"):
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### Source Audio 1")
+                        gr.Audio(audio_files["EN"]["source1"], label="Source 1")
+                    with gr.Column():
+                        gr.Markdown("### Prompts")
+                        gr.Audio(audio_files["EN"]["prompt1"][0], label="Prompt 1")
+                        gr.Audio(audio_files["EN"]["prompt1"][1], label="Prompt 2")
+
+                    with gr.Column():
+                        gr.Markdown("### Converted Audio")
+                        gr.Audio(audio_files["EN"]["gen1"][0], label="Converted 1")
+                        gr.Audio(audio_files["EN"]["gen1"][1], label="Converted 2")
+
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### Source Audio 2")
+                        gr.Audio(audio_files["EN"]["source2"], label="Source 2")
+                    with gr.Column():
+                        gr.Markdown("### Prompts")
+                        gr.Audio(audio_files["EN"]["prompt2"][0], label="Prompt 1")
+                        gr.Audio(audio_files["EN"]["prompt2"][1], label="Prompt 2")
+
+                    with gr.Column():
+                        gr.Markdown("### Converted Audio")
+                        gr.Audio(audio_files["EN"]["gen2"][0], label="Converted 1")
+                        gr.Audio(audio_files["EN"]["gen2"][1], label="Converted 2")
+
+            with gr.TabItem("Chinese (ZH)"):
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### Source Audio 1")
+                        gr.Audio(audio_files["ZH"]["source1"], label="Source 1")
+                    with gr.Column():
+                        gr.Markdown("### Prompts")
+                        gr.Audio(audio_files["ZH"]["prompt3"][0], label="Prompt 1")
+                        gr.Audio(audio_files["ZH"]["prompt3"][1], label="Prompt 2")
+
+                    with gr.Column():
+                        gr.Markdown("### Converted Audio")
+                        gr.Audio(audio_files["ZH"]["gen3"][0], label="Converted 1")
+                        gr.Audio(audio_files["ZH"]["gen3"][1], label="Converted 2")
+
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### Source Audio 2")
+                        gr.Audio(audio_files["ZH"]["source2"], label="Source 2")
+                    with gr.Column():
+                        gr.Markdown("### Prompts")
+                        gr.Audio(audio_files["ZH"]["prompt4"][0], label="Prompt 1")
+                        gr.Audio(audio_files["ZH"]["prompt4"][1], label="Prompt 2")
+
+                    with gr.Column():
+                        gr.Markdown("### Converted Audio")
+                        gr.Audio(audio_files["ZH"]["gen4"][0], label="Converted 1")
+                        gr.Audio(audio_files["ZH"]["gen4"][1], label="Converted 2")
+
+    return demo
+
+
+if __name__ == "__main__":
+    demo = create_audio_demo()
+    demo.launch()