Spaces:
Runtime error
Runtime error
File size: 3,918 Bytes
837713d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
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 = "ylacombe/parler_tts_300M_v0.09"
# TODO: change repo id
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 = 41
default_text = "Please surprise me and speak in whatever voice you enjoy."
title = "# Parler-TTS </div>"
examples = [
[
"'This is the best time of my life, Bartley,' she said happily.",
"A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
],
[
"Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom. ",
"A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
],
[
"montrose also after having experienced still more variety of good and bad fortune threw down his arms and retired out of the kingdom",
"A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a lot of background noise and an animated tone.",
],
]
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)
css = """
#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;
flex: unset !important;
}
#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 !important;
}
#share-btn-container div:nth-child(-n+2){
width: auto !important;
min-height: 0px !important;
}
#share-btn-container .wrap {
display: none !important;
}
"""
with gr.Blocks(css=css) as block:
gr.Markdown(title)
with gr.Row():
with gr.Column():
input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
run_button = gr.Button("Generate Audio", variant="primary")
with gr.Column():
audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out")
inputs = [input_text, description]
outputs = [audio_out]
gr.Examples(examples=examples, fn=gen_tts, inputs=inputs, outputs=outputs, cache_examples=True)
run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
block.queue()
block.launch(share=True)
|