Duplicate from doevent/vc

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.gitignore

@@ -0,0 +1 @@
+__pycache__

README.md

@@ -0,0 +1,13 @@
+---
+title: VC
+emoji: 💬
+colorFrom: blue
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.42.0
+app_file: app.py
+pinned: false
+duplicated_from: doevent/vc
+---
+
+Interactive demo for Voice Conversion service by Balacoon.

app.py

@@ -0,0 +1,68 @@
+import gradio as gr
+import logging
+import os
+from TTS.api import TTS
+import time
+
+tts = TTS(model_name="voice_conversion_models/multilingual/vctk/freevc24", progress_bar=False, gpu=False)
+logging.basicConfig(level=logging.INFO)
+count = 0
+
+def main():
+    global count
+    count += 1
+    if count > 50:
+        time.sleep(5)
+        os.system("rm -R /tmp/*")
+        count = 0
+        
+    with gr.Blocks() as demo:
+
+        with gr.Row():
+            with gr.Column(variant="panel"):
+                src_audio_mic = gr.Audio(source="microphone", label="Record your voice")
+                src_audio_file = gr.Audio(
+                    source="upload", type="filepath", label="Or upload audio to convert"
+                )
+
+            with gr.Column(variant="panel"):
+                tgt_audio_file = gr.Audio(
+                    source="upload", type="filepath", label="Select audio with target voice"
+                )
+
+        with gr.Row():
+            convert_btn = gr.Button("Convert")
+        with gr.Row():
+            result_audio = gr.Audio()
+
+        
+        def voice_conversion(src_from_mic_, src_from_file_, tgt_from_file_):
+            """
+            helper function which checks where source come from
+            """
+            src_ = None
+            if src_from_mic_:
+                src_ = src_from_mic_
+            elif src_from_file_:
+                src_ = src_from_file_
+            tgt_ = tgt_from_file_
+            if not src_ or not tgt_:
+                logging.warning("source or target are not provided")
+                return
+
+            print(src_)
+            print(tgt_)
+            tts.voice_conversion_to_file(source_wav=src_, target_wav=tgt_, file_path="output.wav")
+            return "output.wav"
+        
+        convert_btn.click(
+            voice_conversion,
+            inputs=[src_audio_mic, src_audio_file, tgt_audio_file],
+            outputs=result_audio,
+        )
+
+    demo.queue(concurrency_count=1).launch(show_api=False, show_error=True)
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1 @@
+TTS