Set new standard voices

.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

@@ -97,23 +97,38 @@ def generate(
     return (MODEL.sr, wav.squeeze(0).cpu().numpy())
 
 
+VOICE_OPTIONS = {
+    "mic": "samples/mic_trimmed.wav",
+    "nic": "samples/nic_trimmed.wav"
+}
+
+def update_ref_audio(voice_name):
+    return VOICE_OPTIONS.get(voice_name, list(VOICE_OPTIONS.values())[0])
+
 with gr.Blocks(title="Chatterbox Turbo") as demo:
     gr.Markdown("# ⚡ Chatterbox Turbo")
 
     with gr.Row():
         with gr.Column():
             text = gr.Textbox(
-                value="Oh, that's hilarious! [chuckle] Um anyway, we do have a new model in store. It's the SkyNet T-800 series and it's got basically everything. Including AI integration with ChatGPT and all that jazz. Would you like me to get some prices for you?",
+                value="København er Danmarks hovedstad og ligger på øerne Sjælland og Amager, hvor mange turister besøger de smukke kanaler og historiske bygninger.",
                 label="Text to synthesize (max chars 300)",
                 max_lines=5,
                 elem_id="main_textbox"
             )
 
+            voice = gr.Dropdown(
+                choices=list(VOICE_OPTIONS.keys()),
+                value="mic",
+                label="Voice Selection",
+                info="Choose a voice or upload your own below"
+            )
+
             ref_wav = gr.Audio(
                 sources=["upload", "microphone"],
                 type="filepath",
                 label="Reference Audio File",
-                value="https://storage.googleapis.com/chatterbox-demo-samples/turbo/2.wav",
+                value=VOICE_OPTIONS["mic"],
             )
 
             run_btn = gr.Button("Generate ⚡", variant="primary")
@@ -130,6 +145,12 @@ with gr.Blocks(title="Chatterbox Turbo") as demo:
                 min_p = gr.Slider(0.00, 1.00, step=0.01, label="Min P (Set to 0 to disable)", value=0.00)
                 norm_loudness = gr.Checkbox(value=True, label="Normalize Loudness (-27 LUFS)")
 
+    voice.change(
+        fn=update_ref_audio,
+        inputs=[voice],
+        outputs=[ref_wav],
+    )
+
     run_btn.click(
         fn=generate,
         inputs=[

samples/mic_trimmed.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b33d20de00571adcb1b02bb6601d65c47c8013985652ac54239f7dc0e7d19c0
+size 1461102

samples/nic_trimmed.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6026bc4e1ef0ec9d8e6d49b601fb7960023a545577685fd556be23387ff6b462
+size 1555332