Upload app.py

app.py

@@ -1,11 +1,73 @@
 import subprocess
 import os
 import gradio as gr
-import json
 from utils import *
 from unidecode import unidecode
 from transformers import AutoTokenizer
 
+description = """
+<div>
+<a style="display:inline-block" href='https://github.com/suno-ai/bark'><img src='https://img.shields.io/github/stars/suno-ai/bark?style=social' /></a>
+<a style='display:inline-block' href='https://discord.gg/J2B2vsjKuE'><img src='https://dcbadge.vercel.app/api/server/J2B2vsjKuE?compact=true&style=flat' /></a>
+<a style="display:inline-block; margin-left: 1em" href="https://huggingface.co/spaces/suno/bark?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space%20to%20skip%20the%20queue-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
+</div>
+Bark is a universal text-to-audio model created by [Suno](www.suno.ai), with code publicly available [here](https://github.com/suno-ai/bark). \
+Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. \
+This demo should be used for research purposes only. Commercial use is strictly prohibited. \
+The model output is not censored and the authors do not endorse the opinions in the generated content. \
+Use at your own risk.
+"""
+
+article = """
+## 🌎 Foreign Language
+Bark supports various languages out-of-the-box and automatically determines language from input text. \
+When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.
+Try the prompt:
+```
+Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.
+```
+## 🤭 Non-Speech Sounds
+Below is a list of some known non-speech sounds, but we are finding more every day. \
+Please let us know if you find patterns that work particularly well on Discord!
+* [laughter]
+* [laughs]
+* [sighs]
+* [music]
+* [gasps]
+* [clears throat]
+* — or ... for hesitations
+* ♪ for song lyrics
+* capitalization for emphasis of a word
+* MAN/WOMAN: for bias towards speaker
+Try the prompt:
+```
+" [clears throat] Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as... ♪ singing ♪."
+```
+## 🎶 Music
+Bark can generate all types of audio, and, in principle, doesn't see a difference between speech and music. \
+Sometimes Bark chooses to generate text as music, but you can help it out by adding music notes around your lyrics.
+Try the prompt:
+```
+♪ In the jungle, the mighty jungle, the lion barks tonight ♪
+```
+## 🧬 Voice Cloning
+Bark has the capability to fully clone voices - including tone, pitch, emotion and prosody. \
+The model also attempts to preserve music, ambient noise, etc. from input audio. \
+However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from.
+## 👥 Speaker Prompts
+You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc. \
+Please note that these are not always respected, especially if a conflicting audio history prompt is given.
+Try the prompt:
+```
+WOMAN: I would like an oatmilk latte please.
+MAN: Wow, that's expensive!
+```
+## Details
+Bark model by [Suno](https://suno.ai/), including official [code](https://github.com/suno-ai/bark) and model weights. \
+Gradio demo supported by 🤗 Hugging Face. Bark is licensed under a non-commercial license: CC-BY 4.0 NC, see details on [GitHub](https://github.com/suno-ai/bark).
+"""
+
+
 CLAMP_MODEL_NAME = 'clamp-small-512'
 QUERY_MODAL = 'music'
 KEY_MODAL = 'text'
@@ -199,4 +261,19 @@ input_class10 = gr.inputs.Textbox(label="Class 10", placeholder="Description of
 # output labels with their probabilities
 output_class = gr.outputs.Label(num_top_classes=10, label="Predicted Results")
 
-gr.Interface(zero_shot_music_classification, inputs=[input_file, input_class1, input_class2, input_class3, input_class4, input_class5, input_class6, input_class7, input_class8, input_class9, input_class10], outputs=output_class, title="Zero-Shot Music Classification", description="Upload a MusicXML file and get the class of the music").launch()
+gr.Interface(zero_shot_music_classification,
+             inputs=[input_file, 
+                     input_class1, 
+                     input_class2, 
+                     input_class3, 
+                     input_class4, 
+                     input_class5, 
+                     input_class6, 
+                     input_class7, 
+                     input_class8, 
+                     input_class9, 
+                     input_class10], 
+            outputs=output_class, 
+            title="🗜️ CLaMP: Zero-Shot Music Classification", description="Upload a MusicXML file and get the class of the music",
+            description=description,
+            article=article).launch()