Spaces:
Runtime error
Runtime error
| import spaces | |
| import gradio as gr | |
| import json | |
| import torch | |
| import wavio | |
| from tqdm import tqdm | |
| from huggingface_hub import snapshot_download | |
| from pydub import AudioSegment | |
| from gradio import Markdown | |
| import uuid | |
| import torch | |
| from diffusers import DiffusionPipeline,AudioPipelineOutput | |
| from transformers import CLIPTextModel, T5EncoderModel, AutoModel, T5Tokenizer, T5TokenizerFast | |
| from typing import Union | |
| from diffusers.utils.torch_utils import randn_tensor | |
| from tqdm import tqdm | |
| from TangoFlux import TangoFluxInference | |
| import torchaudio | |
| tangoflux = TangoFluxInference(name="declare-lab/TangoFlux") | |
| def gradio_generate(prompt, steps, guidance,duration=10): | |
| output = tangoflux.generate(prompt,steps=steps,guidance_scale=guidance,duration=duration) | |
| #output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu() | |
| #wavio.write(output_filename, output_wave, rate=44100, sampwidth=2) | |
| filename = 'temp.wav' | |
| #print(f"Saving audio to file: {unique_filename}") | |
| # Save to file | |
| torchaudio.save(filename, output, 44100) | |
| print(f"Audio saved: {unique_filename}") | |
| # Return the path to the generated audio file | |
| return filename | |
| #if (output_format == "mp3"): | |
| # AudioSegment.from_wav("temp.wav").export("temp.mp3", format = "mp3") | |
| # output_filename = "temp.mp3" | |
| #return output_filename | |
| description_text = """ | |
| <p><a href="https://huggingface.co/spaces/declare-lab/tango2/blob/main/app.py?duplicate=true"> <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> For faster inference without waiting in queue, you may duplicate the space and upgrade to a GPU in the settings. <br/><br/> | |
| Generate audio using Tango2 by providing a text prompt. Tango2 was built from Tango and was trained on <a href="https://huggingface.co/datasets/declare-lab/audio-alpaca">Audio-alpaca</a> | |
| <br/><br/> This is the demo for Tango2 for text to audio generation: <a href="https://arxiv.org/abs/2404.09956">Read our paper.</a> | |
| <p/> | |
| """ | |
| # Gradio input and output components | |
| input_text = gr.Textbox(lines=2, label="Prompt") | |
| #output_format = gr.Radio(label = "Output format", info = "The file you can dowload", choices = "wav"], value = "wav") | |
| output_audio = gr.Audio(label="Generated Audio", type="filepath") | |
| denoising_steps = gr.Slider(minimum=10, maximum=100, value=25, step=5, label="Steps", interactive=True) | |
| guidance_scale = gr.Slider(minimum=1, maximum=10, value=4.5, step=0.5, label="Guidance Scale", interactive=True) | |
| duration_scale = gr.Slider(minimum=1, maximum=30, value=10, step=1, label="Duration", interactive=True) | |
| # Gradio interface | |
| gr_interface = gr.Interface( | |
| fn=gradio_generate, | |
| inputs=[input_text, denoising_steps, guidance_scale,duration_scale], | |
| outputs=output_audio, | |
| title="TangoFlux: ", | |
| description=description_text, | |
| allow_flagging=False, | |
| examples=[ | |
| ["Quiet speech and then and airplane flying away"], | |
| ["A bicycle peddling on dirt and gravel followed by a man speaking then laughing"], | |
| ["Ducks quack and water splashes with some animal screeching in the background"], | |
| ["Describe the sound of the ocean"], | |
| ["A woman and a baby are having a conversation"], | |
| ["A man speaks followed by a popping noise and laughter"], | |
| ["A cup is filled from a faucet"], | |
| ["An audience cheering and clapping"], | |
| ["Rolling thunder with lightning strikes"], | |
| ["A dog barking and a cat mewing and a racing car passes by"], | |
| ["Gentle water stream, birds chirping and sudden gun shot"], | |
| ["A man talking followed by a goat baaing then a metal gate sliding shut as ducks quack and wind blows into a microphone."], | |
| ["A dog barking"], | |
| ["A cat meowing"], | |
| ["Wooden table tapping sound while water pouring"], | |
| ["Applause from a crowd with distant clicking and a man speaking over a loudspeaker"], | |
| ["two gunshots followed by birds flying away while chirping"], | |
| ["Whistling with birds chirping"], | |
| ["A person snoring"], | |
| ["Motor vehicles are driving with loud engines and a person whistles"], | |
| ["People cheering in a stadium while thunder and lightning strikes"], | |
| ["A helicopter is in flight"], | |
| ["A dog barking and a man talking and a racing car passes by"], | |
| ], | |
| cache_examples="lazy", # Turn on to cache. | |
| ) | |
| gr_interface.queue(15).launch() |