php网站跟随导航,西安百姓网免费发布信息网,伊滨区网站建设,网络营销渠道可以分为一、简介
开源项目#xff0c;文本提示的生成音频模型
https://github.com/suno-ai/bark Bark是由Suno创建的基于变换器的文本到音频模型。Bark可以生成极为逼真的多语种演讲以及其他音频 - 包括音乐、背景噪音和简单的声音效果。该模型还可以产生非言语沟通#xff0c;如…一、简介
开源项目文本提示的生成音频模型
https://github.com/suno-ai/bark Bark是由Suno创建的基于变换器的文本到音频模型。Bark可以生成极为逼真的多语种演讲以及其他音频 - 包括音乐、背景噪音和简单的声音效果。该模型还可以产生非言语沟通如笑声、叹息和哭声。为了支持研究社区我们提供了预训练的模型检查点可用于推断并可供商业使用。
二、演示链接:
https://pan.baidu.com/s/1O9_la6TBar75NfI1yut4Lg?pwdutqg 提取码: utqg
三、支持的语言
LanguageStatusEnglish (en)✅German (de)✅Spanish (es)✅French (fr)✅Hindi (hi)✅Italian (it)✅Japanese (ja)✅Korean (ko)✅Polish (pl)✅Portuguese (pt)✅Russian (ru)✅Turkish (tr)✅Chinese, simplified (zh)✅
显卡信息 四、安装步骤
1.安装conda
2.安装python3.9
conda create --name brakAI python3.9
3.激活brakAI环境
conda activate barkAI
4.安装 pytorc
conda install pytorch2.0.0 torchvision0.15.0 torchaudio2.0.0 pytorch-cuda11.7 -c pytorch -c nvidia
5.查看了版本
import torch
print(torch.cuda.is_available())
print(torch.__version__) 6.克隆bark
git clone https://github.com/suno-ai/bark
cd bark pip install . 7.测试
from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav
from IPython.display import Audio# download and load all models
preload_models()# generate audio from text
text_prompt CSDN是全球知名中文IT技术交流平台,创建于1999年,包含原创博客、精品问答、职业培训、技术论坛、资源下载等产品服务,提供原创、优质、完整内容的专业IT技术开发社区.。audio_array generate_audio(text_prompt)# save audio to disk
write_wav(bark_generation22.wav, SAMPLE_RATE, audio_array)# play text in notebook
Audio(audio_array, rateSAMPLE_RATE)
会自动下载模型文件text_2.pt也可以自己下载suno/bark at main
模型路径 bark/generation.py 将临时目录改到bark 根目录模型文件下载到这个目录下 五、网页版提供服务 后端main.pyp
# -*- coding: utf-8 -*-
from flask import Flask, request, send_file, render_template_string ,jsonify
from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav
import tempfile
import time
import osapp Flask(__name__)# 下载和加载所有模型
preload_models()app.route(/)
def index():return render_template_string(open(templates/index.html).read())app.route(/generate, methods[POST])
def generate():text_prompt request.form.get(text)if text_prompt:text_prompt request.form[text]audio_array generate_audio(text_prompt)timestamp str(int(time.time()))filename timestamp times.wavfilepath os.path.join(wavfile, filename)write_wav(filepath, SAMPLE_RATE, audio_array)file_url /wavfile/ filenamereturn jsonify({file_url: file_url})else:return No text provided!, 400if __name__ __main__:app.run(host0.0.0.0 ,debugTrue)前端index.html
!DOCTYPE html
html langen
headmeta charsetUTF-8meta nameviewport contentwidthdevice-width, initial-scale1.0titleText to Audio/titlelink relstylesheet hrefhttps://cdn.jsdelivr.net/npm/bootstrap4.0.0/dist/css/bootstrap.min.css integritysha384-Gn5384xqQ1aoWXA058RXPxPg6fy4IWvTNh0E263XmFcJlSAwiGgFAW/dAiS6JXm crossoriginanonymous
script srchttps://cdn.jsdelivr.net/npm/bootstrap4.0.0/dist/js/bootstrap.min.js integritysha384-JZR6Spejh4U02d8jOt6vLEHfe/JQGiRRSQQxSfFWpi1MquVdAyjUar576PVCmYl crossoriginanonymous/script
/head
bodydiv classcontainer mt-5h1Text to Audio Converter By 3yuan 2023.8.22 23.15.00/h1div classform-grouplabel fortextEnter your text:/labeltextarea classform-control idtext rows4 required/textarea/divbutton idconvert classbtn btn-primaryConvert/buttondiv classmt-3a hrefhttps://blog.csdn.net/jxyk2007/article/details/132425993?Open Source TTSgtx1080cuda11.7condapython3.9 ,Beat Baidu TTS/a/divimg idloading classimg-responsive mt-3 src{{ url_for(static, filenameloading.gif) }} styledisplay: none; altLoading...div idresult classmt-3/divdiv idresult2 classmt-3/div/divscript srchttps://code.jquery.com/jquery-3.3.1.min.js/scriptscript$(#convert).click(function() {var text $(#text).val();if (text) {$(#loading).show();$.post(/generate, { text: text }, function(data) {$(#loading).hide();var link $(a href data.file_url download data.file_url Download the audio file/a);$(#result).html(link);var link2 $( video src data.file_url data-canonical-src data.file_url controlscontrols autoplayautoplay stylemax-height:200px; min-height: 100px/video);$(#result2).html(link2);});} else {alert(Please enter some text!);}});/script
/body
/html 其他模型下载文字转语言
Models - Hugging Face
