Duplicate from coraKong/voice-cloning-demo

Co-authored-by: Cora Kong <[email protected]>

.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

README.md

@@ -0,0 +1,13 @@
+---
+title: Voice Cloning Demo
+emoji: 💩
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 3.21.0
+app_file: app.py
+pinned: false
+duplicated_from: coraKong/voice-cloning-demo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+from TTS.api import TTS
+
+# Init TTS
+tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)
+zh_tts = TTS(model_name="tts_models/zh-CN/baker/tacotron2-DDC-GST", progress_bar=False, gpu=False)
+de_tts = TTS(model_name="tts_models/de/thorsten/vits", gpu=False)
+es_tts = TTS(model_name="tts_models/es/mai/tacotron2-DDC", progress_bar=False, gpu=False)
+
+def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
+    if speaker_wav_file and not speaker_wav:
+        speaker_wav = speaker_wav_file
+    file_path = "output.wav"
+    if language == "zh-CN":
+        # if speaker_wav is not None:
+        #     zh_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
+        # else:
+        zh_tts.tts_to_file(text, file_path=file_path)
+    elif language == "de":
+        # if speaker_wav is not None:
+        #     de_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
+        # else:
+        de_tts.tts_to_file(text, file_path=file_path)
+    elif language == "es":
+        # if speaker_wav is not None:
+        #     es_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
+        # else:
+        es_tts.tts_to_file(text, file_path=file_path)
+    else:
+        if speaker_wav is not None:
+            tts.tts_to_file(text, speaker_wav=speaker_wav, language=language, file_path=file_path)
+        else:
+            tts.tts_to_file(text, speaker=tts.speakers[0], language=language, file_path=file_path)
+    return file_path
+
+
+
+# inputs = [gr.Textbox(label="Input the text", value="", max_lines=3),
+#           gr.Audio(label="Voice to clone", source="microphone", type="filepath"),
+#           gr.Audio(label="Voice to clone", type="filepath"), 
+#           gr.Radio(label="Language", choices=["en", "zh-CN", "fr-fr", "pt-br", "de", "es"], value="en"),     
+#           gr.Text(intro_text, font_size=14)]
+# outputs = gr.Audio(label="Output")
+
+# demo = gr.Interface(fn=text_to_speech, inputs=inputs, outputs=outputs)
+
+# demo.launch()
+
+
+title = "Voice-Cloning-Demo"
+
+def toggle(choice):
+    if choice == "mic":
+        return gr.update(visible=True, value=None), gr.update(visible=False, value=None)
+    else:
+        return gr.update(visible=False, value=None), gr.update(visible=True, value=None)
+
+def handle_language_change(choice):
+    if choice == "zh-CN" or choice == "de" or choice == "es":
+        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
+    else:
+        return gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
+
+warming_text = """Please note that Chinese, German, and Spanish are currently not supported for voice cloning."""
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            text_input = gr.Textbox(label="Input the text", value="", max_lines=3)
+            lan_input = gr.Radio(label="Language", choices=["en", "fr-fr", "pt-br", "zh-CN", "de", "es"], value="en")
+            gr.Markdown(warming_text)
+            radio = gr.Radio(["mic", "file"], value="mic",
+                             label="How would you like to upload your audio?")
+            audio_input_mic = gr.Audio(label="Voice to clone", source="microphone", type="filepath", visible=True)
+            audio_input_file = gr.Audio(label="Voice to clone", type="filepath", visible=False)
+
+            with gr.Row():
+                with gr.Column():
+                    btn_clear = gr.Button("Clear")
+                with gr.Column():
+                    btn = gr.Button("Submit", variant="primary")
+        with gr.Column():
+            audio_output = gr.Audio(label="Output")
+
+    # gr.Examples(examples, fn=inference, inputs=[audio_file, text_input],
+    #                   outputs=audio_output, cache_examples=True)
+    btn.click(text_to_speech, inputs=[text_input, audio_input_mic,
+              audio_input_file, lan_input], outputs=audio_output)
+    radio.change(toggle, radio, [audio_input_mic, audio_input_file])
+    lan_input.change(handle_language_change, lan_input, [radio, audio_input_mic, audio_input_file])
+
+demo.launch(enable_queue=True)

requirements.txt

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