Upload 3 files

README.md

@@ -4,8 +4,7 @@ emoji: 🐶
 colorFrom: gray
 colorTo: blue
 sdk: gradio
-sdk_version: 3.27.0
-python_version: 3.8.15
+sdk_version: 5.42.0
 app_file: app.py
 pinned: false
 license: cc-by-nc-4.0

app.py

@@ -1,3 +1,4 @@
+import spaces
 import numpy as np
 import gradio as gr
 from bark import SAMPLE_RATE, generate_audio, preload_models
@@ -117,6 +118,7 @@ examples = [
 ]
 
 
+@spaces.GPU(duration=59)
 def gen_tts(text, history_prompt):  # , temp_semantic, temp_waveform):
     history_prompt = PROMPT_LOOKUP[history_prompt]
     if DEBUG_MODE:
@@ -169,11 +171,9 @@ with gr.Blocks(css=css) as block:
     gr.Markdown(description)
     with gr.Row():
         with gr.Column():
-            input_text = gr.Textbox(
-                label="Input Text", lines=2, value=default_text, elem_id="input_text")
-            options = gr.Dropdown(
-                AVAILABLE_PROMPTS, value="Speaker 1 (en)", label="Acoustic Prompt", elem_id="speaker_option")
-            run_button = gr.Button(text="Generate Audio", type="button")
+            input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
+            options = gr.Dropdown(AVAILABLE_PROMPTS, value="Speaker 1 (en)", label="Acoustic Prompt", elem_id="speaker_option")
+            run_button = gr.Button("Generate Audio")
         with gr.Column():
             audio_out = gr.Audio(label="Generated Audio",
                                  type="numpy", elem_id="audio_out")
@@ -181,9 +181,8 @@ with gr.Blocks(css=css) as block:
                 with gr.Group(elem_id="share-btn-container"):
                     community_icon = gr.HTML(community_icon_html)
                     loading_icon = gr.HTML(loading_icon_html)
-                    share_button = gr.Button(
-                        "Share to community", elem_id="share-btn")
-                    share_button.click(None, [], [], _js=share_js)
+                    share_button = gr.Button("Share to community", elem_id="share-btn")
+                    share_button.click(None, [], [], js=share_js)
     inputs = [input_text, options]
     outputs = [audio_out]
     gr.Examples(examples=examples, fn=gen_tts, inputs=inputs,

requirements.txt

@@ -1,5 +1,11 @@
 git+https://github.com/suno-ai/bark.git
-https://download.pytorch.org/whl/nightly/pytorch_triton-2.1.0%2B46672772b4-cp38-cp38-linux_x86_64.whl
-https://download.pytorch.org/whl/nightly/cu117/torch-2.1.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
-https://download.pytorch.org/whl/nightly/cu117/torchvision-0.16.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
-https://download.pytorch.org/whl/nightly/cu117/torchaudio-2.1.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
+torch==2.1.0
+torchvision
+torchaudio
+triton
+numpy<2
+#https://download.pytorch.org/whl/nightly/pytorch_triton-2.1.0%2B46672772b4-cp38-cp38-linux_x86_64.whl
+#https://download.pytorch.org/whl/nightly/cu117/torch-2.1.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
+#https://download.pytorch.org/whl/nightly/cu117/torchvision-0.16.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
+#https://download.pytorch.org/whl/nightly/cu117/torchaudio-2.1.0.dev20230413%2Bcu117-cp38-cp38-linux_x86_64.whl
+pydantic==2.10.6