feat: worked vixtts

app.py

@@ -6,7 +6,7 @@ import torch
 import torchaudio
 
 # download for mecab
-# os.system("python -m unidic download")
+os.system("python -m unidic download")
 
 # By using XTTS you agree to CPML license https://coqui.ai/cpml
 os.environ["COQUI_TOS_AGREED"] = "1"
@@ -394,159 +394,6 @@ Supported languages: Arabic: ar, Brazilian Portuguese: pt , Mandarin Chinese: zh
 article = """
 
 """
-examples = [
-    [
-        "Once when I was six years old I saw a magnificent picture",
-        "en",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image",
-        "fr",
-        "examples/male.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Als ich sechs war, sah ich einmal ein wunderbares Bild",
-        "de",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Cuando tenía seis años, vi una vez una imagen magnífica",
-        "es",
-        "examples/male.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Quando eu tinha seis anos eu vi, uma vez, uma imagem magnífica",
-        "pt",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Kiedy miałem sześć lat, zobaczyłem pewnego razu wspaniały obrazek",
-        "pl",
-        "examples/male.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno",
-        "it",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Bir zamanlar, altı yaşındayken, muhteşem bir resim gördüm",
-        "tr",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Когда мне было шесть лет, я увидел однажды удивительную картинку",
-        "ru",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Toen ik een jaar of zes was, zag ik op een keer een prachtige plaat",
-        "nl",
-        "examples/male.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "Když mi bylo šest let, viděl jsem jednou nádherný obrázek",
-        "cs",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "当我还只有六岁的时候， 看到了一副精彩的插画",
-        "zh-cn",
-        "examples/female.wav",
-        None,
-        False,
-        False,
-        False,
-        True,
-    ],
-    [
-        "かつて 六歳のとき、素晴らしい絵を見ました",
-        "ja",
-        "examples/female.wav",
-        None,
-        False,
-        True,
-        False,
-        True,
-    ],
-    [
-        "한번은 내가 여섯 살이었을 때 멋진 그림을 보았습니다.",
-        "ko",
-        "examples/female.wav",
-        None,
-        False,
-        True,
-        False,
-        True,
-    ],
-    [
-        "Egyszer hat éves koromban láttam egy csodálatos képet",
-        "hu",
-        "examples/male.wav",
-        None,
-        False,
-        True,
-        False,
-        True,
-    ],
-]
-
 
 with gr.Blocks(analytics_enabled=False) as demo:
     with gr.Row():
@@ -601,7 +448,7 @@ with gr.Blocks(analytics_enabled=False) as demo:
                 label="Reference Audio",
                 info="Click on the ✎ button to upload your own target speaker audio",
                 type="filepath",
-                value="examples/female.wav",
+                value="model/samples/nu-luu-loat.wav",
             )
             mic_gr = gr.Audio(
                 source="microphone",
@@ -638,25 +485,6 @@ with gr.Blocks(analytics_enabled=False) as demo:
             out_text_gr = gr.Text(label="Metrics")
             ref_audio_gr = gr.Audio(label="Reference Audio Used")
 
-    with gr.Row():
-        gr.Examples(
-            examples,
-            label="Examples",
-            inputs=[
-                input_text_gr,
-                language_gr,
-                ref_gr,
-                mic_gr,
-                use_mic_gr,
-                clean_ref_gr,
-                auto_det_lang_gr,
-                tos_gr,
-            ],
-            outputs=[video_gr, audio_gr, out_text_gr, ref_audio_gr],
-            fn=predict,
-            cache_examples=False,
-        )
-
     tts_button.click(
         predict,
         [