Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,29 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+inference_output/Billie[[:space:]]Jean_converted_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Billie[[:space:]]Jean_original_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Dirty[[:space:]]Diana_converted_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Dirty[[:space:]]Diana_original_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Heal[[:space:]]the[[:space:]]World_converted_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Heal[[:space:]]the[[:space:]]World_original_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Man[[:space:]]in[[:space:]]the[[:space:]]mirror_converted_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/Man[[:space:]]in[[:space:]]the[[:space:]]mirror_original_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/billiejean_converted_mix.wav filter=lfs diff=lfs merge=lfs -text
+inference_output/billiejean_original_mix.wav filter=lfs diff=lfs merge=lfs -text
+people/Biden/image.png filter=lfs diff=lfs merge=lfs -text
+people/Drake/image.png filter=lfs diff=lfs merge=lfs -text
+people/Harry[[:space:]]Styles/image.png filter=lfs diff=lfs merge=lfs -text
+people/Obama/image.png filter=lfs diff=lfs merge=lfs -text
+people/Post[[:space:]]Malone/image.png filter=lfs diff=lfs merge=lfs -text
+songs/Beat[[:space:]]It/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Beat[[:space:]]It/vocals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Billie[[:space:]]Jean/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Billie[[:space:]]Jean/vocals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Dirty[[:space:]]Diana/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Dirty[[:space:]]Diana/vocals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Heal[[:space:]]the[[:space:]]World/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Heal[[:space:]]the[[:space:]]World/vocals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Man[[:space:]]in[[:space:]]the[[:space:]]mirror/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
+songs/Man[[:space:]]in[[:space:]]the[[:space:]]mirror/vocals.wav filter=lfs diff=lfs merge=lfs -text
+songs/cover.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,19 @@
+people/biden/G_20000.pth
+people/brunomars/G_124930.pth
+people/jimin/G_24000.pth
+people/obama/G_50000.pth
+people/Alicia Keys/G_6018.pth
+people/Billie Eilish/G_8000.pth
+people/Bruna Mars/G_124930.pth
+people/Drake/G_106000.pth
+people/Eninem/G_203200.pth
+people/Freddie Mercury/G_300000.pth
+people/Harry Styles/G_5143.pth
+people/Homer Simpson/G_22000.pth
+people/Jimin/G_24000.pth
+people/Lady Gaga/G_14400.pth
+people/Obama/G_50000.pth
+people/Post Malone/G_9600.pth
+people/Taylor Swift/G_7600.pth
+people/Usher/G_33600.pth
+.env

LICENSE

@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.

README.md

@@ -1,12 +1,75 @@
 ---
-title: Voice-Blend Alchemy-AI
-emoji: 🌖
-colorFrom: indigo
-colorTo: blue
+title: Voice-Blend_Alchemy-AI
+app_file: code_v2.py
 sdk: gradio
 sdk_version: 4.19.2
-app_file: app.py
-pinned: false
 ---
+<div align="center">
+  
+![VoiceIt](https://i.imgur.com/DendqCA.png)
+  
+<a href="https://github.com/ImPavloh/VoiceIt" target="_blank"><img src="https://img.shields.io/github/license/impavloh/voiceit?style=for-the-badge&logo=github&logoColor=white"></a>
+<a href="https://twitter.com/ImPavloh" target="_blank"><img src="https://img.shields.io/badge/Follow-%231DA1F2.svg?style=for-the-badge&logo=twitter&logoColor=white"></a>
+<a href="https://voiceit.pavloh.com" target="_blank"><img alt="Online use" src="https://img.shields.io/badge/WEBSITE-401769?style=for-the-badge&logo=react&logoColor=white"></a>
+<a href="https://huggingface.co/spaces/ImPavloh/voiceit/tree/main" target="_blank"><img src="https://img.shields.io/badge/HuggingFace-%23E06011.svg?style=for-the-badge"></a>
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<p><strong>README Language</strong></p>
+<a href="README.md"><img alt="English" src="https://unpkg.com/language-icons/icons/en.svg" width="50px" style="border-top-left-radius: 25px; border-bottom-left-radius: 25px;"></a>
+<a href="README_es.md"><img alt="Spanish" src="https://unpkg.com/language-icons/icons/es.svg" width="50px"></a>
+
+</div>
+
+# 🎙️ VoiceIt!
+
+This project uses pre-trained models to change the voice in audio files. The service allows you to upload audio files, select a voice model, and generate a new audio file with the modified voice.
+
+# 📚 Relevant Information 🚀
+
+You can use VoiceIt directly online on my website **https://voiceit.pavloh.com** or use your resources and host the project locally by following the steps below.
+
+### Requirements
+
+- Python >3.7
+- Gradio
+- FFmpeg
+- FFprobe
+
+### 🛠️ Installation
+
+1. Clone the repository:
+`git clone https://github.com/impavloh/voiceit.git`
+
+2. Change to the project directory:
+`cd voiceit`
+
+3. Install the necessary dependencies:
+`pip install -r requirements.txt`
+
+4. Create a folder called "models" and import pre-trained models to use later. In this case, you can use my models: 
+https://huggingface.co/ImPavloh/Streamers-AI-Voices
+
+5. Run the main script:
+`python voiceit.py`
+
+### 📝 Usage
+
+1. When running the voiceit.py file, a terminal will open with a link to access the VoiceIt! interface. For example: `http://localhost:7860`
+
+2. Select a voice model from the dropdown list.
+
+3. Upload an audio file.
+
+4. Click on the "Change voice" button to generate a new audio file with the modified voice.
+
+5. Listen or download the result in the audio player.
+
+6. You can delete the data and restart the process using the "Delete" button.
+
+## ⚠️ Warning
+
+- Audio files should contain only one voice and be free of noise or background music.
+- The conversion time will depend on the duration of the audio and web usage (if used locally it will depend on your resources)
+
+## 📝 License and Terms of Use
+
+> By using this project, you agree to the [license](https://raw.githubusercontent.com/ImPavloh/VoiceIt/main/LICENSE) and [terms of use](https://raw.githubusercontent.com/ImPavloh/VoiceIt/main/TERMINOS_DE_USO.txt).

README_es.md

@@ -0,0 +1,69 @@
+<div align="center">
+  
+![VoiceIt](https://i.imgur.com/DendqCA.png)
+  
+<a href="https://github.com/ImPavloh/VoiceIt" target="_blank"><img src="https://img.shields.io/github/license/impavloh/voiceit?style=for-the-badge&logo=github&logoColor=white"></a>
+<a href="https://twitter.com/ImPavloh" target="_blank"><img src="https://img.shields.io/badge/Seguir-%231DA1F2.svg?style=for-the-badge&logo=twitter&logoColor=white"></a>
+<a href="https://huggingface.co/spaces/ImPavloh/voiceit/tree/main" target="_blank"><img src="https://img.shields.io/badge/HuggingFace-%23E06011.svg?style=for-the-badge"></a>
+
+<p><strong>Idioma del README</strong></p>
+<a href="README.md"><img alt="English" src="https://unpkg.com/language-icons/icons/en.svg" width="50px" style="border-top-left-radius: 25px; border-bottom-left-radius: 25px;"></a>
+<a href="README_es.md"><img alt="Spanish" src="https://unpkg.com/language-icons/icons/es.svg" width="50px"></a>
+
+**[Usar VoiceIt! online](https://voiceit.pavloh.com)**
+</div>
+
+# 🎙️ VoiceIt!
+
+Este proyecto utiliza modelos pre-entrenados para cambiar la voz en archivos de audio. El servicio permite cargar archivos de audio, seleccionar un modelo de voz y generar un nuevo archivo de audio con la voz modificada.
+
+# 📚 Información relevante 🚀
+
+Puedes utilizar VoiceIt! online directamente en mi web **https://voiceit.pavloh.com** o utilizar tus recursos y alojar el proyecto localmente siguiendo los siguientes pasos.
+
+### Requisitos
+
+- Python >3.7
+- Gradio
+- FFmpeg
+- FFprobe
+
+### 🛠️ Instalación
+
+1. Clona el repositorio:
+`git clone https://github.com/impavloh/voiceit.git`
+
+2. Cambia al directorio del proyecto:
+`cd voiceit`
+
+3. Instala las dependencias necesarias:
+`pip install -r requirements.txt`
+
+4. Crea una carpeta llamada "modelos" e importa modelos pre-entrenados para utilizar más tarde. En este caso puedes utilizar mis modelos: 
+https://huggingface.co/ImPavloh/Streamers-AI-Voices
+
+5. Ejecuta el script principal:
+`python voiceit.py`
+
+### 📝 Uso
+
+1. Al ejecutar el archivo voiceit.py se abrirá un terminal con un enlace para poder acceder a la interfaz de VoiceIt!. Por ejemplo: `http://localhost:7860`
+
+2. Selecciona un modelo de voz de la lista desplegable.
+
+3. Carga un archivo de audio.
+
+4. Haz clic en el botón "Cambiar voz" para generar un nuevo archivo de audio con la voz modificada.
+
+5. Escucha o descarga el resultado en el reproductor de audio.
+
+6. Puedes borrar los datos y reiniciar el proceso utilizando el botón "Borrar".
+
+## ⚠️ Advertencia
+
+- Los archivos de audio deben contener solo una voz y estar libres de ruido o música de fondo.
+- El tiempo de conversión dependerá de la duración del audio y del uso de la web (en caso de utilizarlo localmente dependerá de tus recursos)
+
+## 📝 Licencia y términos de uso
+
+> Al utilizar este proyecto, aceptas la [licencia](https://raw.githubusercontent.com/ImPavloh/VoiceIt/main/LICENSE) y los [términos de uso](https://raw.githubusercontent.com/ImPavloh/VoiceIt/main/TERMINOS_DE_USO.txt).

code_v2.py

@@ -0,0 +1,271 @@
+from threading import Thread
+from pathlib import Path
+import gradio as gr
+import subprocess
+import shutil
+import time
+import copy
+import glob
+import json
+import os
+import shlex
+import numpy as np
+import librosa
+from scipy.io import wavfile
+import openai
+from openai import OpenAI
+from dotenv import load_dotenv
+from PIL import Image
+import requests
+from io import BytesIO
+
+load_dotenv()
+
+OpenAI.api_key = os.getenv('OPENAI_API_KEY')
+
+logo_image_path = "Logo.png"  
+alchemy_image_path = "Alchemy AI.png"  
+technation_logo_blk = "technation_logo_blk.png"
+
+
+client = OpenAI(
+)
+
+# Paths according to your directory structure
+CURRENT_DIR = Path(__file__).resolve().parent
+PEOPLE_DIR = CURRENT_DIR / "people"
+SONGS_DIR = CURRENT_DIR / "songs"
+INFERENCE_OUTPUT_DIRNAME = CURRENT_DIR / "inference_output"
+COVER_IMAGE_PATH = SONGS_DIR / "cover.png"
+
+# Ensure the inference output directory exists
+INFERENCE_OUTPUT_DIRNAME.mkdir(parents=True, exist_ok=True)
+
+def get_people():
+    """List the people available for voice conversion."""
+    return sorted([p.stem for p in PEOPLE_DIR.iterdir() if p.is_dir()])
+
+def get_songs():
+    """List the song directories available for selection."""
+    # Use a set to avoid adding duplicate folder names
+    folder_names = set()
+    # Iterate through all directories and subdirectories in SONGS_DIR
+    for root, dirs, _ in os.walk(SONGS_DIR):
+        for dir in dirs:
+            # Construct the relative path from SONGS_DIR to the current directory
+            relative_path = os.path.relpath(os.path.join(root, dir), SONGS_DIR)
+            # Add the relative path of directories to the set
+            folder_names.add(relative_path)
+    # Return a sorted list of unique folder names
+    return sorted(folder_names)
+
+
+def run_inference(speaker, path_str, f0_method, transpose, noise_scale, cluster_ratio):
+    # Ensure path is a Path object
+    path = Path(path_str)
+
+    model_path = speaker["model_path"]
+    config_path = speaker["cfg_path"]
+    cluster_path = speaker["cluster_path"]
+    output_path = Path(INFERENCE_OUTPUT_DIRNAME, path.name)  # Now path is guaranteed to be a Path object
+    cluster_args = f"-k \"{cluster_path}\" -r {cluster_ratio}" if cluster_path and cluster_ratio > 0 else ""
+    
+    # Ensure output directory exists
+    INFERENCE_OUTPUT_DIRNAME.mkdir(parents=True, exist_ok=True)
+    
+    inference_cmd = f"svc infer \"{path.absolute()}\" -m \"{model_path}\" -c \"{config_path}\" {cluster_args} -t {transpose} --f0-method crepe -n 0.4 -o \"{output_path}\" --no-auto-predict-f0"
+    command = shlex.split(inference_cmd)
+    result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+    
+    if result.returncode != 0:
+        print(f"Command failed with return code {result.returncode}")
+        print("STDERR:", result.stderr)
+        return None, "⚠️ Error during inference."
+    
+    if "AttributeError" in result.stderr:
+        return None, "⚠️ Modelo SVC incompatible."
+    
+    if not output_path.exists():
+        print("Expected output file not found:", output_path)
+        return None, "⚠️ Error: Output file not found."
+    
+    return str(output_path), None
+
+def get_speaker_details(speaker_name):
+    speakers = []  # This should ideally be a list of dictionaries
+    # Assuming MODELOS is a directory containing subdirectories for each speaker/model
+    for _, dirs, _ in os.walk(PEOPLE_DIR):
+        for dir_name in dirs:
+            if dir_name.lower() == speaker_name.lower():
+                speaker_path = PEOPLE_DIR / dir_name
+                model_path = next(speaker_path.glob('G_*.pth'), None)
+                description_path = speaker_path / "description.txt"
+                image_path = next(speaker_path.glob('image.png'), None) 
+                cfg_path = next(speaker_path.glob('*.json'), None)
+                if model_path and cfg_path:
+                    return {
+                        "model_path": model_path,
+                        "cfg_path": cfg_path,
+                        "description_path": description_path, 
+                        "cluster_path": "",
+                        "image_path": image_path                        
+                    }
+    return None
+
+def mix_audio(vocals_path, instrumentals_path, output_path):
+    y_vocals, sr = librosa.load(vocals_path, sr=None)
+    y_instrumentals, _ = librosa.load(instrumentals_path, sr=None)
+
+    # Ensure both tracks are of the same length
+    max_length = max(len(y_vocals), len(y_instrumentals))
+    y_vocals_padded = np.pad(y_vocals, (0, max_length - len(y_vocals)), mode='constant')
+    y_instrumentals_padded = np.pad(y_instrumentals, (0, max_length - len(y_instrumentals)), mode='constant')
+
+    # Mix the two audio files
+    mixed_audio = 0.5 * y_vocals_padded + 0.5 * y_instrumentals_padded
+
+    # Save the mixed audio to a new WAV file
+    wavfile.write(output_path, sr, (mixed_audio * 32767).astype(np.int16))
+
+def gen_caption_image(song_name, person):
+    prompt = f"Create a creative and engaging Instagram caption for a post where {person} is performing the song '{song_name}'. Make it exciting and suitable for social media."
+
+    response = client.chat.completions.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "user", "content": prompt}
+        ]
+        )
+    
+    caption= response.choices[0].message.content
+
+    image_prompt=f'draw an image for my instagram post having for the song {song_name} and the caption {caption}'
+
+    responseimage = client.images.generate(
+        model="dall-e-3",
+        prompt=image_prompt,
+        size="1024x1024",
+        quality="standard",
+        n=1,
+        )
+    image_url = responseimage.data[0].url
+
+    image_response = requests.get(image_url)
+    img = Image.open(BytesIO(image_response.content))
+    
+
+    return np.array(img) , caption
+
+def voice_conversion(person, song_selection):
+    try:
+        speaker_details = get_speaker_details(person)
+        if not speaker_details:
+            raise Exception("Speaker not found! Error: Speaker details not found.")
+
+        # Extract the folder name from the song selection (ignoring the file part)
+        folder_name = song_selection.split('\\')[0]
+
+        vocals_path = SONGS_DIR / folder_name / "vocals.wav"
+        instrumentals_path = SONGS_DIR / folder_name / "instrumentals.wav"
+
+        if not vocals_path.exists() or not instrumentals_path.exists():
+            raise Exception(f"Vocals or instrumentals not found in {folder_name}! Error: Audio file not found.")
+
+        converted_vocals_path, error = run_inference(speaker_details, str(vocals_path), 0, 0, 0.4, 0)
+        if error:
+            raise Exception(error)
+
+        converted_mix_path = str(INFERENCE_OUTPUT_DIRNAME / f"{folder_name}_converted_mix.wav")
+        mix_audio(converted_vocals_path, str(instrumentals_path), converted_mix_path)
+
+        return converted_mix_path
+    except Exception as e:
+        return None, None, str(e), "" 
+
+def update_person_details(selected_person):
+    speaker_details = get_speaker_details(selected_person)
+    image_path = str(speaker_details["image_path"])
+    # Return the image path in a list as expected by the Gallery component
+    with open(speaker_details["description_path"], 'r') as file:
+        person_description = file.read()
+    return image_path, person_description
+
+
+
+def update_song_features(song_selection):
+    cover_image_path = COVER_IMAGE_PATH
+    folder_name = song_selection.split('\\')[0]
+    vocals_path = SONGS_DIR / folder_name / "vocals.wav"
+    instrumentals_path = SONGS_DIR / folder_name / "instrumentals.wav"
+    if not vocals_path.exists() or not instrumentals_path.exists():
+        raise Exception(f"Vocals or instrumentals not found in {folder_name}! Error: Audio file not found.")
+
+    original_mix_path = str(INFERENCE_OUTPUT_DIRNAME / f"{folder_name}_original_mix.wav")
+    mix_audio(str(vocals_path), str(instrumentals_path), original_mix_path)
+
+    return original_mix_path, cover_image_path
+
+# Updating the interface setup to include the event listener
+
+# CSS for artistic theme
+# CSS for artistic theme and custom positioning
+css = """
+@import url('https://fonts.googleapis.com/css2?family=Pacifico&display=swap');
+.center-container {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+}
+.right-container {
+    display: flex;
+    justify-content: flex-end;
+    align-items: center;
+}
+/* Additional custom CSS for spacing and alignment */
+.logo-img {
+    max-width: 100%;
+    height: auto;
+    display: block;
+    margin-left: auto;
+    margin-right: auto;
+}
+.alchemy-img {
+    float: right;
+    max-height: 60px; /* Adjust based on your preference */
+}
+"""
+
+# Gradio app with custom CSS and theme
+with gr.Blocks(css=css) as app:
+    with gr.Row():
+            gr.Image(logo_image_path, container=False, show_label=False, show_download_button=False)
+
+
+
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("#### Step 1: Pick Your Track 🎵")
+            song_dropdown = gr.Dropdown(label="Pick one of 5 songs:", choices=get_songs())
+            album_image = gr.Image(label="Cover Image", height=300)
+            original_mix_audio = gr.Audio(label="Original Mix (Vocals + Instrumentals)", interactive=False)
+            song_dropdown.change(fn=update_song_features, inputs=song_dropdown, outputs=[original_mix_audio, album_image])
+
+        with gr.Column():
+            gr.Markdown("#### Step 2: Select Your Voice to Emulate 👩🏻")
+            person_dropdown = gr.Dropdown(label="Select one of 15 voices:", choices=get_people())
+            person_image = gr.Image(label="Person", height=300)
+            person_description_text = gr.Textbox(label="Description:")
+            person_dropdown.change(update_person_details, inputs=person_dropdown, outputs=[person_image, person_description_text])
+            
+            convert_button = gr.Button("Convert")
+
+        with gr.Column():
+            gr.Markdown("#### Your Custom AI Vocal - Unveiled! 🤖")
+            converted_mix_audio = gr.Audio(label="Converted Mix (Converted Vocals + Instrumentals)", type="filepath")
+            convert_button.click(voice_conversion, inputs=[person_dropdown, song_dropdown], outputs=[converted_mix_audio])
+
+            generate_button = gr.Button("Generate Caption and Image")
+            generate_button.click(gen_caption_image, inputs=[song_dropdown, person_dropdown], outputs=[gr.Image(label="Generated Image", type="numpy", height=300), gr.Textbox(label="Generated Caption")])
+
+if __name__ == "__main__":
+    app.launch(share = True)

hugging_face_models.txt

@@ -0,0 +1,9 @@
+EN
+All the pre-trained models needed to use "VoiceIt!" are in Hugging Face, in case you want to use your own model remember that only SVC models work.
+|
+|- SVC models already trained for VoiceIt - [https://huggingface.co/spaces/ImPavloh/voiceit/tree/main/modelos]
+
+ES
+Todos los modelos pre-entrenados necesarios para poder utilizar "VoiceIt!" se encuentran en Hugging Face, en caso de que quieras utilizar tu propio modelo recuerda que solo funcionan modelos SVC.
+|
+|- Modelos SVC ya entrenados para VoiceIt - [https://huggingface.co/spaces/ImPavloh/voiceit/tree/main/modelos]

inference_output/Billie Jean_converted_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dab4a392ad7028f4c73362884ab22465ced9259698a126d94e3ea1c47c9a3e2
+size 1764044

inference_output/Billie Jean_original_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c50d391e1fa218cb794b9631bb8dc5af5bf67b9065422acfe2a4449d679779
+size 1764044

inference_output/Dirty Diana_converted_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3732df0471e2d442ea017a7d1df18408e7b47e7e592f06914a21aec526fa74c
+size 1234844

inference_output/Dirty Diana_original_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5bdc26b93dae71c1141ee23aa20ae45208822f874e5d87456997178774bcc6
+size 1234844

inference_output/Heal the World_converted_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352a8209680d331c1e078c0041f0b867f734a0ed985b444ec5058bc80cc35272
+size 2109562

inference_output/Heal the World_original_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d6fa14844327d60c2cd70b190e392a6e08b016bc57d3c6843864f4936f825d
+size 2109562

inference_output/Man in the mirror_converted_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6faea9a8a3350d35669b109ec90778cd9bad55a1e7289b21a6939a88dc1c4c6f
+size 1411244

inference_output/Man in the mirror_original_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db16db29ffccac8e1f328d7aa623b7dbd7e021842f00acd0cfdbb9b582efd55
+size 1411244

inference_output/billiejean_converted_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8531b948b3520ee72cd93614543a3c6923240101a13173962d522c199c3e5e7b
+size 1764044

inference_output/billiejean_original_mix.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c50d391e1fa218cb794b9631bb8dc5af5bf67b9065422acfe2a4449d679779
+size 1764044

people/Alicia Keys/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 30000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 24,
+    "fp16_run": false,
+    "bf16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "num_workers": 40,
+    "log_version": 0,
+    "ckpt_name_by_step": false,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "Keys": 0
+  }
+}

people/Alicia Keys/description.txt

@@ -0,0 +1 @@
+Alicia Keys is an American singer-songwriter and musician known for her soulful voice, classical piano skills, and blending elements of R&B, soul, and jazz in her music, along with her advocacy for social justice and HIV/AIDS awareness.

people/Biden/config.json

@@ -0,0 +1,93 @@
+{
+  "train": {
+    "log_interval": 100,
+    "eval_interval": 500,
+    "seed": 1234,
+    "epochs": 10001,
+    "learning_rate": 0.00015,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/Biden/train.txt",
+    "validation_files": "filelists/Biden/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "Biden": 0
+  }
+}

people/Biden/description.txt

@@ -0,0 +1 @@
+A seasoned politician known for his long tenure in U.S. government and leadership as the President.

people/Billie Eilish/config.json

@@ -0,0 +1,94 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050,
+    "contentvec_final_proj": false
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 768,
+    "n_speakers": 200
+  },
+  "spk": {
+    "BEV": 0
+  }
+}

people/Billie Eilish/description.txt

@@ -0,0 +1 @@
+Billie Eilish is an American singer-songwriter known for her ethereal indie pop sound, whispery vocals, and introspective lyrics, who gained fame as a teenager and has since become a leading voice in modern pop music with a distinctive style.

people/Bruna Mars/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 4805,
+    "seed": 1234,
+    "epochs": 4040,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 8,
+    "fp16_run": false,
+    "bf16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "num_workers": 4,
+    "log_version": 0,
+    "ckpt_name_by_step": true,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "BrunoMars": 0
+  }
+}

people/Bruna Mars/description.txt

@@ -0,0 +1 @@
+A dynamic performer recognized for his catchy pop and R&B hits, and energetic live performances.

people/Drake/config.json

@@ -0,0 +1,93 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "drake01": 0
+  }
+}

people/Drake/description.txt

@@ -0,0 +1 @@
+Drake is a Canadian rapper, singer, and actor known for his emotive rap and R&B style, significant influence on modern hip hop, and numerous chart-topping hits.

people/Eninem/config.json

@@ -0,0 +1,94 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "all_in_mem": false
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 1
+  },
+  "spk": {
+    "ACAPELLAS FINAL": 0
+  }
+}

people/Eninem/description.txt

@@ -0,0 +1 @@
+Eminem is an American rapper, songwriter, and record producer known for his controversial and influential work in hip hop, characterized by his complex lyrics, rapid flow, and ability to alter his persona.

people/Freddie Mercury/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 100,
+    "eval_interval": 250,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 16,
+    "fp16_run": false,
+    "bf16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "num_workers": 4,
+    "log_version": 0,
+    "ckpt_name_by_step": true,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "freddie mercury": 0
+  }
+}

people/Freddie Mercury/description.txt

@@ -0,0 +1 @@
+Freddie Mercury was a British singer-songwriter and the lead vocalist of the rock band Queen, known for his flamboyant stage presence, powerful vocal range, and iconic hits that blend rock, opera, and other genres, leaving a lasting legacy in music history.

people/Harry Styles/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 16,
+    "fp16_run": false,
+    "bf16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "num_workers": 4,
+    "log_version": 0,
+    "ckpt_name_by_step": false,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "harry": 0
+  }
+}

people/Harry Styles/description.txt

@@ -0,0 +1 @@
+Harry Styles is an English singer, songwriter, and actor who gained fame as a member of the boy band One Direction and has since established a successful solo career, known for his distinctive voice, eclectic fashion sense, and music that spans pop, rock, and folk genres.

people/Homer Simpson/config.json

@@ -0,0 +1,94 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050,
+    "contentvec_final_proj": false
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 768,
+    "n_speakers": 200
+  },
+  "spk": {
+    "homersimpson": 0
+  }
+}

people/Homer Simpson/description.txt

@@ -0,0 +1 @@
+Homer Simpson is a fictional character from the animated television series "The Simpsons," known for his love of donuts and beer, his bumbling yet endearing personality, and his role as the comically inept patriarch of the Simpson family.

people/Jimin/config.json

@@ -0,0 +1,94 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "all_in_mem": false
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 1
+  },
+  "spk": {
+    "44k": 0
+  }
+}

people/Jimin/description.txt

@@ -0,0 +1 @@
+A globally celebrated K-pop idol, known for his exceptional dance skills and vocal talent as part of the group BTS.