Added tab to read and copy settings from a voice clip (in the future, I'll see about enmbedding the latent used to generate the voice)

app.py

@@ -130,7 +130,7 @@ def generate(text, delimiter, emotion, prompt, voice, mic_audio, preset, seed, c
 
     info = {
         'text': text,
-        'delimiter': delimiter,
+        'delimiter': '\\n' if delimiter == "\n" else delimiter,
         'emotion': emotion,
         'prompt': prompt,
         'voice': voice,
@@ -185,11 +185,44 @@ def update_presets(value):
     else:
         return (gr.update(), gr.update())
 
+def read_metadata(file):
+    j = None
+    if file is not None:
+        metadata = music_tag.load_file(file.name)
+        if 'lyrics' in metadata:
+            j = json.loads(str(metadata['lyrics']))
+            print(j)
+    return j
+
+def copy_settings(file):
+    metadata = read_metadata(file)
+    if metadata is None:
+        return None
+
+    return (
+        metadata['text'],
+        metadata['delimiter'],
+        metadata['emotion'],
+        metadata['prompt'],
+        metadata['voice'],
+        metadata['mic_audio'],
+        metadata['preset'],
+        metadata['seed'],
+        metadata['candidates'],
+        metadata['num_autoregressive_samples'],
+        metadata['diffusion_iterations'],
+        metadata['temperature'],
+        metadata['diffusion_sampler'],
+        metadata['breathing_room'],
+        metadata['experimentals'],
+    )
+
 def update_voices():
     return gr.Dropdown.update(choices=os.listdir(os.path.join("tortoise", "voices")) + ["microphone"])
 
 def main():
-    with gr.Blocks() as demo:
+    with gr.Blocks() as webui:
+        with gr.Tab("Generate"):
             with gr.Row():
                 with gr.Column():
                     text = gr.Textbox(lines=4, label="Prompt")
@@ -266,8 +299,7 @@ def main():
                     submit = gr.Button(value="Generate")
                     #stop = gr.Button(value="Stop")
                     
-                submit_event = submit.click(generate,
-                    inputs=[
+                    input_settings = [
                         text,
                         delimiter,
                         emotion,
@@ -283,13 +315,34 @@ def main():
                         diffusion_sampler,
                         breathing_room,
                         experimentals,
-                    ],
+                    ]
+
+                    submit_event = submit.click(generate,
+                        inputs=input_settings,
                         outputs=[selected_voice, output_audio, usedSeed],
                     )
 
                     #stop.click(fn=None, inputs=None, outputs=None, cancels=[submit_event])
+        with gr.Tab("Utilities"):
+            with gr.Row():
+                with gr.Column():
+                    audio_in = gr.File(type="file", label="Audio Input", file_types=["audio"])
+                    copy_button = gr.Button(value="Copy Settings")
+                with gr.Column():
+                    metadata_out = gr.JSON(label="Audio Metadata")
 
-    demo.queue().launch(share=args.share)
+                    audio_in.upload(
+                        fn=read_metadata,
+                        inputs=audio_in,
+                        outputs=metadata_out,
+                    )
+
+                    copy_button.click(copy_settings,
+                        inputs=audio_in, # JSON elements cannt be used as inputs
+                        outputs=input_settings
+                    )
+
+    webui.queue().launch(share=args.share)
 
 
 if __name__ == "__main__":
@@ -299,6 +352,7 @@ if __name__ == "__main__":
     parser.add_argument("--cond-latent-max-chunk-size", type=int, default=1000000, help="Sets an upper limit to audio chunk size when computing conditioning latents")
     args = parser.parse_args()
 
+    print("Initializating TorToiSe...")
     tts = TextToSpeech(minor_optimizations=not args.low_vram)
 
     main()