app.py

import gradio as gr
import torch

from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed

device = "cuda:0" if torch.cuda.is_available() else "cpu"


repo_id = "parler-tts/parler_tts_mini_v0.1"

model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
tokenizer = AutoTokenizer.from_pretrained(repo_id)
feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)


SAMPLE_RATE = feature_extractor.sampling_rate
SEED = 42

def gen_tts(text, description):
    inputs = tokenizer(description, return_tensors="pt").to(device)
    prompt = tokenizer(text, return_tensors="pt").to(device)

    set_seed(SEED)
    generation = model.generate(
        input_ids=inputs.input_ids, prompt_input_ids=prompt.input_ids, do_sample=True, temperature=1.0
    )
    audio_arr = generation.cpu().numpy().squeeze()

    return SAMPLE_RATE, audio_arr


with gr.Blocks(css=css) as block:
   gr.HTML("""
        <div style="z-index: 100; position: fixed; top: 0px; right: 0px; left: 0px; bottom: 0px; width: 100%; height: 100%; background: white; display: flex; align-items: center; justify-content: center; color: black;">
        <div style="text-align: center; color: black;">
        <p style="color: black;">This space is a headless component of the cloud rendering engine used by AiTube.</p>
        <p style="color: black;">It is not available for public use, but you can use the <a href="https://huggingface.co/spaces/ByteDance/AnimateDiff-Lightning" target="_blank">original space</a>.</p>
        </div>
        </div>""")
    with gr.Row():
        input_text = gr.Textbox(label="Input Text")
        description = gr.Textbox(label="Description")
        run_button = gr.Button("Generate Audio")
        audio_out = gr.Textbox()

    inputs = [input_text, description]
    outputs = [audio_out]
    run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)


block.queue()
block.launch(share=True)