from huggingface_hub import hf_hub_download import torch import os import gradio as gr from audioldm2 import text_to_audio, build_model from share_btn import community_icon_html, loading_icon_html, share_js os.environ["TOKENIZERS_PARALLELISM"] = "true" default_checkpoint="audioldm2-full" audioldm = None current_model_name = None def text2audio( text, guidance_scale, random_seed, n_candidates, model_name=default_checkpoint, ): global audioldm, current_model_name torch.set_float32_matmul_precision("high") if audioldm is None or model_name != current_model_name: audioldm = build_model(model_name=model_name) current_model_name = model_name audioldm = torch.compile(audioldm) # print(text, length, guidance_scale) waveform = text_to_audio( latent_diffusion=audioldm, text=text, seed=random_seed, duration=10, guidance_scale=guidance_scale, n_candidate_gen_per_text=int(n_candidates), ) # [bs, 1, samples] waveform = [ gr.make_waveform((16000, wave[0]), bg_image="bg.png") for wave in waveform ] # waveform = [(16000, np.random.randn(16000)), (16000, np.random.randn(16000))] if len(waveform) == 1: waveform = waveform[0] return waveform css = """ a { color: inherit; text-decoration: underline; } .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: #000000; background: #000000; } input[type='range'] { accent-color: #000000; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } #gallery { min-height: 22rem; margin-bottom: 15px; margin-left: auto; margin-right: auto; border-bottom-right-radius: .5rem !important; border-bottom-left-radius: .5rem !important; } #gallery>div>.h-full { min-height: 20rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } #advanced-btn { font-size: .7rem !important; line-height: 19px; margin-top: 12px; margin-bottom: 12px; padding: 2px 8px; border-radius: 14px !important; } #advanced-options { margin-bottom: 20px; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .acknowledgments h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } #container-advanced-btns{ display: flex; flex-wrap: wrap; justify-content: space-between; align-items: center; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; margin-top: 10px; margin-left: auto; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0; } #share-btn * { all: unset; } #share-btn-container div:nth-child(-n+2){ width: auto !important; min-height: 0px !important; } #share-btn-container .wrap { display: none !important; } .gr-form{ flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0; } #prompt-container{ gap: 0; } #generated_id{ min-height: 700px } #setting_id{ margin-bottom: 12px; text-align: center; font-weight: 900; } """ iface = gr.Blocks(css=css) with iface: gr.HTML( """
For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings.
Essential Tricks for Enhancing the Quality of Your Generated Audio
1. Try to use more adjectives to describe your sound. For example: "A man is speaking clearly and slowly in a large room" is better than "A man is speaking". This can make sure AudioLDM 2 understands what you want.
2. Try to use different random seeds, which can affect the generation quality significantly sometimes.
3. It's better to use general terms like 'man' or 'woman' instead of specific names for individuals or abstract objects that humans may not be familiar with, such as 'mummy'.
We build the model with data from AudioSet, Freesound and BBC Sound Effect library. We share this demo based on the UK copyright exception of data for academic research.
This demo is strictly for research demo purpose only. For commercial use please contact us.
iface.queue(concurrency_count=3) iface.launch(debug=True) # iface.launch(debug=True, share=True)