iniial commit

Dockerfile

@@ -0,0 +1,21 @@
+FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
+
+
+
+WORKDIR /app
+
+RUN apt-get update
+RUN apt-get install -y  python3-pip git
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip3 install --upgrade pip wheel
+RUN pip install numpy==1.26.2 torch==2.3.0 packaging
+RUN pip install -U flash-attn==2.5.8 
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user app.py /app
+CMD [ "python3", "app.py" ]

README.md

@@ -0,0 +1,10 @@
+---
+title: Valle2 Demo
+emoji: 🌍
+colorFrom: yellow
+colorTo: gray
+sdk: docker
+app_port: 7860
+pinned: false
+---
+

app.py

@@ -0,0 +1,60 @@
+import os
+
+import torch
+import gradio as gr
+
+
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Vocoder
+vocoder = torch.hub.load(repo_or_dir='ex3ndr/supervoice-vocoder', model='bigvsan')
+vocoder.to(device)
+vocoder.eval()
+
+# GPT Model
+gpt = torch.hub.load(repo_or_dir='ex3ndr/supervoice-gpt', model='phonemizer')
+gpt.to(device)
+gpt.eval()
+
+# Main Model
+model = torch.hub.load(repo_or_dir='ex3ndr/supervoice-voicebox', model='phonemizer', gpt=gpt, vocoder=vocoder)
+model.to(device)
+model.eval()
+
+
+
+
+description = f'''
+Voicebox demo
+'''
+
+def synthesise(text, voice):
+    output = model.synthesize(text, voice = voice, steps = 8, alpha = 0.1)
+    waveform = output['wav']
+    return (24000, waveform.numpy())
+
+if __name__ == "__main__":
+    i = gr.Interface(
+        fn=synthesise,
+        description=description,
+        inputs=[
+            gr.Text(label='Text:', lines=5, max_lines=10),
+            gr.Dropdown(label="voice", choices=("voice_1", "voice_2"), value="voice_1"),
+        ],
+        outputs=[
+            gr.Audio(
+                        label="Audio:",
+                        autoplay=False,
+                        streaming=False,
+                        type="numpy",
+                    ),
+            
+        ],
+        allow_flagging ='never',
+        cache_examples=True,
+        title='Something',
+        examples=[         ],
+    )
+    i.queue(max_size=20, default_concurrency_limit=4)
+    i.launch(share=False, server_name="0.0.0.0")

requirements.txt

@@ -0,0 +1,8 @@
+torch==2.3.0
+gradio
+torchaudio
+vocos
+encodec
+sentencepiece
+xformers
+flash-attn