Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 erew123
|
68acd49234 | ||
|
erew123
|
6728a71210 | ||
|
erew123
|
d6cfbfcedf | ||
|
erew123
|
8644a65e58 | ||
|
erew123
|
9306b31c12 | ||
|
erew123
|
ff911ee73d | ||
|
erew123
|
df89623f06 | ||
|
erew123
|
3329257c46 | ||
|
erew123
|
e853efbf94 | ||
|
erew123
|
4fae216a29 | ||
|
erew123
|
99b0a0dc17 | ||
|
erew123
|
ecc619e5fe | ||
|
erew123
|
17de71e59c |
No files matched your search
+1
-1
@@ -1,5 +1,5 @@
|
||||
voices/*.*
|
||||
models/*.*
|
||||
outputs/*.*
|
||||
config.json
|
||||
confignew.json
|
||||
models.json
|
||||
@@ -37,30 +37,23 @@ I could force a delimeter in at this stage, but I know it would/may affect thing
|
||||
## 🟩 Installation on Text generation web UI
|
||||
This has been tested on the current Dec 2023 release of Text generation webUI. If you have not updated it for a while, you may wish to update Text generation webUI, [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
|
||||
|
||||
1) In a command prompt/terminal window you need to move into your Text generation webUI folder:
|
||||
|
||||
1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
|
||||
`cd text-generation-webui`
|
||||
|
||||
2) Start the Text generation webUI Python environment for your OS:
|
||||
|
||||
2) Start the Text generation webUI Python environment for your OS:<br><br>
|
||||
`cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`
|
||||
|
||||
3) Move into your extensions folder:
|
||||
|
||||
3) Move into your extensions folder:<br><br>
|
||||
`cd extensions`
|
||||
|
||||
4) Once there git clone this repository:
|
||||
|
||||
4) Once there git clone this repository:<br><br>
|
||||
`git clone https://github.com/erew123/alltalk_tts`
|
||||
|
||||
5) Move into the **alltalk_tts** folder:
|
||||
|
||||
5) Move into the **alltalk_tts** folder:<br><br>
|
||||
`cd alltalk_tts`
|
||||
|
||||
6) Install the requirements:
|
||||
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`
|
||||
|
||||
6) Install the requirements:<br><br>
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`<br><br>
|
||||
*Other machines (mac, amd etc)* - `pip install -r requirements_other.txt`
|
||||
|
||||
7) **(Optional DeepSpeed)** If you have an Nvidia Graphics card on a system running Linux or Windows and wish to use **DeepSpeed** please follow these instructions [here](https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options). Though you may wish to check things are generally working with the below steps before installing DeepSpeed.
|
||||
@@ -87,26 +80,21 @@ To start AllTalk every Text generation webUI loads, edit the Text generation web
|
||||
### 🟪 Updating
|
||||
This is pretty much a repeat of the installation process.
|
||||
|
||||
1) In a command prompt/terminal window you need to move into your Text generation webUI folder:
|
||||
|
||||
1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
|
||||
`cd text-generation-webui`
|
||||
|
||||
2) Move into your extensions and alltalk_tts folder:
|
||||
|
||||
2) Move into your extensions and alltalk_tts folder:<br><br>
|
||||
`cd extensions` then `cd alltalk_tts`
|
||||
|
||||
3) At the command prompt/terminal, type:
|
||||
|
||||
3) At the command prompt/terminal, type:<br><br>
|
||||
`git pull`
|
||||
|
||||
4) Install the requirements:
|
||||
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`
|
||||
|
||||
4) Install the requirements:<br><br>
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`<br><br>
|
||||
*Other machines (mac, amd etc)* - `pip install -r requirements_other.txt`
|
||||
|
||||
#### 🟪 **git pull error**
|
||||
I did leave a mistake in the `/extensions/alltalk_tts/.gitignore` file at one point. If your `git pull` doesnt work, you can either follow the Problems Updating section below, or edit the `.gitignore` file and **replace its entire contents** with the below, save the file, then re-try the `git pull`
|
||||
I did leave a mistake in the `/extensions/alltalk_tts/.gitignore` file at one point. If your `git pull` doesnt work, you can either follow the Problems Updating section below, or edit the `.gitignore` file and **replace its entire contents** with the below, save the file, then re-try the `git pull`<br><br>
|
||||
```
|
||||
voices/*.*
|
||||
models/*.*
|
||||
@@ -120,26 +108,20 @@ If you do experience any problems, the simplest method to resolve this will be:
|
||||
|
||||
1) re-name the existing `alltalk_tts` folder to something like `alltalk_tts.old`
|
||||
|
||||
2) Start a console/terminal then:
|
||||
|
||||
2) Start a console/terminal then:<br><br>
|
||||
`cd text-generation-webui` and start your python environment `cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`
|
||||
|
||||
3) Move into the extensions folder, same as if you were doing a fresh installation:
|
||||
|
||||
`cd extensions` then
|
||||
|
||||
3) Move into the extensions folder, same as if you were doing a fresh installation:<br><br>
|
||||
`cd extensions` then<br><br>
|
||||
`git clone https://github.com/erew123/alltalk_tts`
|
||||
|
||||
This will download a fresh installation.
|
||||
|
||||
3) Move into the **alltalk_tts** folder:
|
||||
|
||||
3) Move into the **alltalk_tts** folder:<br><br>
|
||||
`cd alltalk_tts`
|
||||
|
||||
4) Install the requirements:
|
||||
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`
|
||||
|
||||
4) Install the requirements:<br><br>
|
||||
*Nvidia graphics card machines* - `pip install -r requirements_nvidia.txt`<br><br>
|
||||
*Other machines (mac, amd etc)* - `pip install -r requirements_other.txt`
|
||||
|
||||
5) Before starting it up, copy/merge the `models`, `voices` and `outputs` folders over from the `alltalk_tts.old` folder to the newly created `alltalk_tts` folder. This will keep your voices history and also stop it re-downloading the model again.
|
||||
@@ -157,7 +139,7 @@ Assuming its all working fine and you are happy, you can delete the old alltalk_
|
||||
|
||||
#### 🟨 I activated DeepSpeed in the settings page, but I didnt install DeepSpeed yet and now I have issues starting up
|
||||
|
||||
You can either follow the [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-updating) and fresh install your config. Or you can edit the `config.json` file within the `alltalk_tts` folder. You would look for '"deepspeed_activate": true,' and change the word true to false `"deepspeed_activate": false,' ,then save the file and try starting again.
|
||||
You can either follow the [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-updating) and fresh install your config. Or you can edit the `confignew.json` file within the `alltalk_tts` folder. You would look for '"deepspeed_activate": true,' and change the word true to false `"deepspeed_activate": false,' ,then save the file and try starting again.
|
||||
|
||||
If you want to use DeepSpeed, you need an Nvidia Graphics card and to install DeepSpeed on your system. Instructions are [here](https://github.com/erew123/alltalk_tts?tab=readme-ov-file#deepspeed-installation-options).
|
||||
|
||||
@@ -171,7 +153,7 @@ As far as I am aware, these are to do with the chrome browser the gradio text-ge
|
||||
|
||||
#### 🟨 I am having problems updating/some other issue where it wont start up/Im sure this is a bug
|
||||
|
||||
Please see [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-updating). If that doesnt help you can raise an issue [here](https://github.com/erew123/alltalk_tts/issues). It would be handy to have any log files from the console where your error is being shown. I can only losely support custom built Python environments and give general pointers.
|
||||
Please see [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-updating). If that doesnt help you can raise an ticket [here](https://github.com/erew123/alltalk_tts/issues). It would be handy to have any log files from the console where your error is being shown. I can only losely support custom built Python environments and give general pointers.
|
||||
|
||||
Also, is your text-generation-webui up to date? [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
|
||||
|
||||
@@ -181,7 +163,7 @@ Also, is your text-generation-webui up to date? [instructions here](https://gith
|
||||
|
||||
Covered in the online/buit-in documentation, but a nice easy install.
|
||||
|
||||
### 🟢🟡 For Windows & Python 3.11
|
||||
### 🟢🟡 For Windows & Python 3.11.x or 3.10.x
|
||||
DeepSpeed v11.1 and v11.2 will work on the current text-generation-webui Python 3.11 environment! You have 2x options for how to setup DeepSpeed on Windows. A quick way (🟢Option 1) and a long way (🟡Option 2).
|
||||
|
||||
Thanks to [@S95Sedan](https://github.com/S95Sedan) - They managed to get DeepSpeed 11.2 working on Windows via making some edits to the original Microsoft DeepSpeed v11.2 installation. The original post is [here](https://github.com/oobabooga/text-generation-webui/issues/4734#issuecomment-1843984142).
|
||||
@@ -190,59 +172,56 @@ Thanks to [@S95Sedan](https://github.com/S95Sedan) - They managed to get DeepSpe
|
||||
#### Pre-Compiled Wheel Deepspeed v11.1 (for Windows and Python 3.11)
|
||||
➡️DeepSpeed requires an Nvidia Graphics card!⬅️
|
||||
|
||||
[@S95Sedan](https://github.com/S95Sedan) has kindly provided a pre-compiled DeepSpeed v11.1 wheel file, which you can download and use. To use this, you will need to:
|
||||
|
||||
**Note:** In my tests, with this method you will **not** need to install the Nvidia CUDA toolkit to make this work, but AllTalk may warn you when starting DeepSpeed that it doesnt see the CUDA Toolkit, however, it works fine for TTS purposes.
|
||||
|
||||
1) Download the file [deepspeed-0.11.1+e9503fe-cp311-cp311-win_amd64.whl](https://drive.google.com/file/d/1PFsf6uSPY5Cb4o9VxiZ7DLv-j35L7Y41/view?usp=sharing) by going to the link and clicking the **download** icon at the top right of the screen and save the file it inside your **text-generation-webui** folder.
|
||||
|
||||
2) Open a command prompt window, move into your **text-generation-webui folder**, you can now start the Python environment for text-generation-webui:
|
||||
1) Download the correct wheel version for your Python/Cuda from [here](https://github.com/erew123/alltalk_tts/releases/tag/deepspeed) and save the file it inside your **text-generation-webui** folder.
|
||||
|
||||
2) Open a command prompt window, move into your **text-generation-webui folder**, you can now start the Python environment for text-generation-webui:<br><br>
|
||||
`cmd_windows.bat`
|
||||
|
||||
3) With the file that you saved in the **text-generation-webui folder** you now type the following:
|
||||
|
||||
3) With the file that you saved in the **text-generation-webui folder** you now type the following:<br><br>
|
||||
`pip install "deepspeed-0.11.1+e9503fe-cp311-cp311-win_amd64.whl"`
|
||||
|
||||
4) This should install through cleanly and you should now have DeepSpeed v11.1 installed within the Python 3.11 environment of text-generation-webui.
|
||||
5) This should install through cleanly and you should now have DeepSpeed v11.1 installed within the Python 3.11 environment of text-generation-webui.
|
||||
|
||||
5) When you start up text-generation-webui, and AllTalk starts, you should see **[AllTalk Startup] DeepSpeed Detected**
|
||||
6) When you start up text-generation-webui, and AllTalk starts, you should see **[AllTalk Startup] DeepSpeed Detected**
|
||||
|
||||
6) Within AllTalk, you will now have a checkbox for **Activate DeepSpeed** though remember you can only change **1x setting every 15 or so seconds**, so dont try to activate DeepSpeed **and** LowVRAM/Change your model simultantiously. Do one of those, wait 15-20 seconds until the change is confirmed in the terminal/command prompt, then you can change the other. When you are happy it works, you can set the default start-up settings in the settings page.
|
||||
7) Within AllTalk, you will now have a checkbox for **Activate DeepSpeed** though remember you can only change **1x setting every 15 or so seconds**, so dont try to activate DeepSpeed **and** LowVRAM/Change your model simultantiously. Do one of those, wait 15-20 seconds until the change is confirmed in the terminal/command prompt, then you can change the other. When you are happy it works, you can set the default start-up settings in the settings page.
|
||||
|
||||
#### 🟡 OPTION 2 - A bit more complicated!
|
||||
#### Manual Build DeepSpeed v11.2 (for Windows and Python 3.11)
|
||||
➡️DeepSpeed requires an Nvidia Graphics card!⬅️
|
||||
|
||||
DeepSpeed Version 11.2 with CUDA 12.1 - Installation Instructions:
|
||||
DeepSpeed Version 11.2 with CUDA 11.8 or 12.1 - Installation Instructions:
|
||||
|
||||
1. Download the 11.2 release of [DeepSpeed](https://github.com/microsoft/DeepSpeed/releases/tag/v0.11.2) extract it to a folder.
|
||||
2. Install Visual C++ build tools, such as [VS2019 C++ x64/x86](https://learn.microsoft.com/en-us/visualstudio/releases/2019/redistribution#vs2019-download) build tools.
|
||||
3. Download and install the [Nvidia Cuda Toolkit 12.1](https://developer.nvidia.com/cuda-12-1-0-download-archive)
|
||||
4. Edit your Windows environment variables to ensure that CUDA_HOME and CUDA_PATH are set to your Nvidia Cuda Toolkit path. (The folder above the bin folder that nvcc.exe is installed in). Examples are:<br>
|
||||
3. Download and install the [Nvidia Cuda Toolkit 11.8 or 12.1](https://developer.nvidia.com/cuda-toolkit-archive)
|
||||
4. OPTIONAL If you do not have an python environment already created, you can install [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/miniconda-install.html), then at a command prompt, create and activate your environment with:<br><br>
|
||||
```conda create -n pythonenv python=3.11```<br>
|
||||
```activate pythonenv```<br><br>
|
||||
If you are using the **text-generation-webui** python environment, then in the `text-generation-webui` folder you will run `cmd_windows.bat` to start the python evnironment.<br>
|
||||
|
||||
5. Launch the Command Prompt cmd with Administrator privilege as it requires admin to allow creating symlink folders.
|
||||
6. Install PyTorch, 2.1.0 with CUDA 12.1 into your Python 3.11 environment e.g:<br><br>
|
||||
```activate pythonenv``` (activate your python environment)<br>
|
||||
```conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia```<br>
|
||||
or<br>
|
||||
```conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=11.8 -c pytorch -c nvidia```<br>
|
||||
7. Edit your Windows environment variables to ensure that CUDA_HOME and CUDA_PATH are set to your Nvidia Cuda Toolkit path. (The folder above the bin folder that nvcc.exe is installed in). Examples are:<br><br>
|
||||
```set CUDA_HOME=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1```<br>
|
||||
```set CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1```<br>
|
||||
rr<br>
|
||||
```set CUDA_HOME=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8```<br>
|
||||
```set CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8```<br>
|
||||
|
||||
5. OPTIONAL If you do not have an python environment already created, you can install [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/miniconda-install.html), then at a command prompt, create and activate your environment with:<br>
|
||||
```conda create -n pythonenv python=3.11```<br>
|
||||
```activate pythonenv```<br>
|
||||
|
||||
6. Launch the Command Prompt cmd with Administrator privilege as it requires admin to allow creating symlink folders.
|
||||
7. Install PyTorch, 2.1.0 with CUDA 12.1 into your Python 3.11 environment e.g:<br>
|
||||
```activate pythonenv``` (activate your python environment)<br>
|
||||
```conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia```
|
||||
|
||||
8. In your python environment check that your CUDA_HOME and CUDA_PATH are still pointing to the correct location.<br>
|
||||
```set``` (to list and check the windows environment variables. Refer to step 4 if not)
|
||||
|
||||
9. Navigate to your deepspeed folder in the Command Prompt:<br>
|
||||
8. Navigate to your deepspeed folder in the Command Prompt:<br><br>
|
||||
```cd c:\deepspeed``` (wherever you extracted it to)
|
||||
|
||||
10. Modify the following files:<br>
|
||||
9. Modify the following files:<br>
|
||||
**(These modified files are included in the git-pull of AllTalk, in the DeepSpeed Windows folder but if you want to modify them yourself, please follow the below)**<br>
|
||||
|
||||
**(These modified files are included in the git-pull of AllTalk, but if you want to modify them yourself, please follow the below)**
|
||||
|
||||
deepspeed-0.11.2/build_win.bat** - at the top of the file, add:<br>
|
||||
deepspeed-0.11.2/build_win.bat** - at the top of the file, add:<br><br>
|
||||
```set DS_BUILD_EVOFORMER_ATTN=0```
|
||||
|
||||
deepspeed-0.11.2/csrc/quantization/pt_binding.cpp - lines 244-250 - change to:
|
||||
@@ -298,10 +277,10 @@ def get_shm_size():
|
||||
return "UNKNOWN", [f"Error getting shared memory size: {e}"]
|
||||
```
|
||||
|
||||
11. While still in your command line with python environment enabled run:<br>
|
||||
```build_win.bat```
|
||||
10. While still in your command line with python environment enabled run:<br>
|
||||
```build_win.bat``` and wait 10-20 minutes.
|
||||
|
||||
12. Now cd dist to go into your dist folder and you can now pip install deepspeed-YOURFILENAME.whl (or whatever your WHL file is called).
|
||||
11. Now `cd dist` to go into your dist folder and you can now `pip install deepspeed-YOURFILENAME.whl` (or whatever your WHL file is called).
|
||||
|
||||
### 🔴 Future to-do list
|
||||
- Complete & document the new/full standalone mode API.
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
{"activate": true, "autoplay": true, "branding": "AllTalk ", "narrator_enabled": false, "deepspeed_activate": false, "delete_output_wavs": "Disabled", "ip_address": "127.0.0.1", "language": "English", "low_vram": false, "local_temperature": "0.7", "local_repetition_penalty": "10.0", "model_loaded": true, "model_name": "tts_models/multilingual/multi-dataset/xtts_v2", "narrator_voice": "female_01.wav", "output_folder_wav": "extensions/alltalk_tts/outputs/", "port_number": "7851", "remove_trailing_dots": false, "show_text": true, "tts_method_api_local": false, "tts_method_api_tts": false, "tts_method_xtts_local": true, "voice": "female_01.wav"}
|
||||
@@ -0,0 +1 @@
|
||||
{"activate": true, "autoplay": true, "branding": "AllTalk ", "narrator_enabled": false, "deepspeed_activate": false, "delete_output_wavs": "Disabled", "ip_address": "127.0.0.1", "language": "English", "low_vram": false, "local_temperature": "0.7", "local_repetition_penalty": "10.0", "tts_model_loaded": true, "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2", "narrator_voice": "female_01.wav", "output_folder_wav": "extensions/alltalk_tts/outputs/", "output_folder_wav_standalone": "outputs/", "port_number": "7851", "remove_trailing_dots": false, "show_text": true, "tts_method_api_local": false, "tts_method_api_tts": false, "tts_method_xtts_local": true, "voice": "female_01.wav"}
|
||||
+4
-4
@@ -6,9 +6,9 @@ import importlib.metadata as metadata
|
||||
import json
|
||||
from packaging import version
|
||||
|
||||
##############################################################
|
||||
#### LOAD PARAMS FROM CONFIG.JSON - REQUIRED FOR BRANDING ####
|
||||
##############################################################
|
||||
#################################################################
|
||||
#### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
|
||||
#################################################################
|
||||
# STARTUP VARIABLE - Create "this_dir" variable as the current script directory
|
||||
this_dir = Path(__file__).parent.resolve()
|
||||
|
||||
@@ -20,7 +20,7 @@ def load_config(file_path):
|
||||
return config
|
||||
|
||||
|
||||
config_file_path = this_dir / "config.json"
|
||||
config_file_path = this_dir / "confignew.json"
|
||||
params = load_config(config_file_path)
|
||||
|
||||
# Define the path to the modeldownload config file file
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
numpy>=1.22.0
|
||||
soundfile>=0.12.1
|
||||
uvicorn>=0.24.0.post1
|
||||
TTS>=0.21.3
|
||||
TTS>=0.22.0
|
||||
torch>=2.1.0+cu118
|
||||
torchaudio>=2.1.0+cu118
|
||||
fastapi>=0.104.1
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
numpy>=1.22.0
|
||||
soundfile>=0.12.1
|
||||
uvicorn>=0.24.0.post1
|
||||
TTS>=0.21.3
|
||||
TTS>=0.22.0
|
||||
torch>=2.1.0
|
||||
torchaudio>=2.1.0
|
||||
fastapi>=0.104.1
|
||||
|
||||
@@ -16,9 +16,9 @@ import numpy as np
|
||||
import soundfile as sf
|
||||
import uuid
|
||||
|
||||
##############################################################
|
||||
#### LOAD PARAMS FROM CONFIG.JSON - REQUIRED FOR BRANDING ####
|
||||
##############################################################
|
||||
#################################################################
|
||||
#### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
|
||||
#################################################################
|
||||
# STARTUP VARIABLE - Create "this_dir" variable as the current script directory
|
||||
this_dir = Path(__file__).parent.resolve()
|
||||
|
||||
@@ -28,8 +28,8 @@ def load_config(file_path):
|
||||
config = json.load(config_file)
|
||||
return config
|
||||
|
||||
config_file_path = this_dir / "config.json"
|
||||
# Load the params dictionary from the config.json file
|
||||
config_file_path = this_dir / "confignew.json"
|
||||
# Load the params dictionary from the confignew.json file
|
||||
params = load_config(config_file_path)
|
||||
|
||||
# Required for sentence splitting
|
||||
@@ -143,9 +143,9 @@ def check_required_files():
|
||||
check_required_files()
|
||||
|
||||
|
||||
#################################################
|
||||
#### SET GRADIO BUTTONS BASED ON CONFIG.JSON ####
|
||||
#################################################
|
||||
####################################################
|
||||
#### SET GRADIO BUTTONS BASED ON confignew.json ####
|
||||
####################################################
|
||||
|
||||
if params["tts_method_api_tts"] == True:
|
||||
gr_modelchoice = "API TTS"
|
||||
@@ -277,7 +277,7 @@ else:
|
||||
# MODEL - Swap model based on Gradio selection API TTS, API Local, XTTSv2 Local
|
||||
def send_reload_request(tts_method):
|
||||
try:
|
||||
params["model_loaded"] = False
|
||||
params["tts_model_loaded"] = False
|
||||
url = f"{base_url}/api/reload"
|
||||
payload = {"tts_method": tts_method}
|
||||
response = requests.post(url, params=payload)
|
||||
@@ -285,8 +285,8 @@ def send_reload_request(tts_method):
|
||||
json_response = response.json()
|
||||
# Check if the reload operation was successful
|
||||
if json_response.get("status") == "model-success":
|
||||
# Update model_loaded to True if the reload was successful
|
||||
params["model_loaded"] = True
|
||||
# Update tts_tts_model_loaded to True if the reload was successful
|
||||
params["tts_model_loaded"] = True
|
||||
# Update local script parameters based on the tts_method
|
||||
if tts_method == "API TTS":
|
||||
params["tts_method_api_local"] = False
|
||||
@@ -319,7 +319,7 @@ def send_reload_request(tts_method):
|
||||
# LOW VRAM - Gradio Checkbox handling
|
||||
def send_lowvram_request(low_vram):
|
||||
try:
|
||||
params["model_loaded"] = False
|
||||
params["tts_model_loaded"] = False
|
||||
if low_vram:
|
||||
audio_path = this_dir / "templates" / "lowvramenabled.wav"
|
||||
else:
|
||||
@@ -332,7 +332,7 @@ def send_lowvram_request(low_vram):
|
||||
# Check if the low VRAM request was successful
|
||||
if json_response.get("status") == "lowvram-success":
|
||||
# Update any relevant variables or perform other actions on success
|
||||
params["model_loaded"] = True
|
||||
params["tts_model_loaded"] = True
|
||||
return f'<audio src="file/{audio_path}" controls autoplay></audio>'
|
||||
except requests.exceptions.RequestException as e:
|
||||
# Handle the HTTP request error
|
||||
@@ -348,7 +348,7 @@ def send_lowvram_request(low_vram):
|
||||
# DEEPSPEED - Reload the model when DeepSpeed checkbox is enabled/disabled
|
||||
def send_deepspeed_request(deepspeed_param):
|
||||
try:
|
||||
params["model_loaded"] = False
|
||||
params["tts_model_loaded"] = False
|
||||
if deepspeed_param:
|
||||
audio_path = this_dir / "templates" / "deepspeedenabled.wav"
|
||||
else:
|
||||
@@ -362,7 +362,7 @@ def send_deepspeed_request(deepspeed_param):
|
||||
# Check if the deepspeed request was successful
|
||||
if json_response.get("status") == "deepspeed-success":
|
||||
# Update any relevant variables or perform other actions on success
|
||||
params["model_loaded"] = True
|
||||
params["tts_model_loaded"] = True
|
||||
return f'<audio src="file/{audio_path}" controls autoplay></audio>'
|
||||
except requests.exceptions.RequestException as e:
|
||||
# Handle the HTTP request error
|
||||
@@ -400,7 +400,7 @@ Synthesizer.split_into_sentences = new_split_into_sentences
|
||||
# Check model is loaded and string isnt empty, before sending a TTS request.
|
||||
def before_audio_generation(string, params):
|
||||
# Check Model is loaded into cuda or cpu and error if not
|
||||
if not params["model_loaded"]:
|
||||
if not params["tts_model_loaded"]:
|
||||
print(
|
||||
f"[{params['branding']}Model] \033[91mWarning\033[0m Model is still loading, please wait before trying to generate TTS"
|
||||
)
|
||||
@@ -789,7 +789,7 @@ def ui():
|
||||
)
|
||||
tts_radio_buttons_play = gr.HTML(visible=False)
|
||||
explanation_text = gr.HTML(
|
||||
f"<p>NOTE: Switching Model Type, Low VRAM & DeepSpeed takes 15 seconds. Each TTS generation method has a slightly different sound. DeepSpeed checkbox is only visible if DeepSpeed is present. Readme & Settings: <a href='http://{params['ip_address']}:{params['port_number']}'>http://{params['ip_address']}:{params['port_number']}</a>"
|
||||
f"<p>NOTE: Switching Model Type, Low VRAM & DeepSpeed, each takes 15 seconds. Each TTS generation method has a slightly different sound. DeepSpeed checkbox is only visible if DeepSpeed is present. Readme & Settings: <a href='http://{params['ip_address']}:{params['port_number']}'>http://{params['ip_address']}:{params['port_number']}</a>"
|
||||
)
|
||||
|
||||
with gr.Row():
|
||||
|
||||
@@ -201,12 +201,12 @@
|
||||
value="{{ data.output_folder_wav }}" />
|
||||
|
||||
|
||||
<input type="hidden" id="model_loaded" name="model_loaded" value="{{ data.model_loaded }}" />
|
||||
<input type="hidden" id="tts_model_loaded" name="tts_model_loaded" value="{{ data.tts_model_loaded }}" />
|
||||
|
||||
<!-- Continue updating other dropdowns and inputs in a similar manner -->
|
||||
|
||||
<label for="model_name" style="color: red;"> API TTS Model Name:</label>
|
||||
<input id="model_name" name="model_name" required="" type="text" value="{{ data.model_name }}" />
|
||||
<label for="tts_model_name" style="color: red;"> API TTS Model Name:</label>
|
||||
<input id="tts_model_name" name="tts_model_name" required="" type="text" value="{{ data.tts_model_name }}" />
|
||||
|
||||
<label for="model_version"
|
||||
style="color: red; font-size: 16px; line-height: 1; vertical-align: bottom; margin-bottom: 0;">
|
||||
|
||||
+32
-29
@@ -35,9 +35,9 @@ with open(this_dir / "languages.json", encoding="utf8") as f:
|
||||
languages = json.load(f)
|
||||
|
||||
|
||||
##############################################################
|
||||
#### LOAD PARAMS FROM CONFIG.JSON - REQUIRED FOR BRANDING ####
|
||||
##############################################################
|
||||
#################################################################
|
||||
#### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
|
||||
#################################################################
|
||||
# Load config file and get settings
|
||||
def load_config(file_path):
|
||||
with open(file_path, "r") as configfile_path:
|
||||
@@ -45,10 +45,10 @@ def load_config(file_path):
|
||||
return configfile_data
|
||||
|
||||
|
||||
# Define the path to the config.json file
|
||||
configfile_path = this_dir / "config.json"
|
||||
# Define the path to the confignew.json file
|
||||
configfile_path = this_dir / "confignew.json"
|
||||
|
||||
# Load config.json and assign it to a different variable (config_data)
|
||||
# Load confignew.json and assign it to a different variable (config_data)
|
||||
params = load_config(configfile_path)
|
||||
# check someone hasnt enabled lowvram on a system thats not cuda enabled
|
||||
params["low_vram"] = "false" if not torch.cuda.is_available() else params["low_vram"]
|
||||
@@ -131,7 +131,7 @@ async def setup():
|
||||
# Start loading the correct model as set by "tts_method_api_tts", "tts_method_api_local" or "tts_method_xtts_local" being True/False
|
||||
if params["tts_method_api_tts"]:
|
||||
print(
|
||||
f"[{params['branding']}Model] \033[94mAPI TTS Loading\033[0m {params['model_name']} \033[94minto\033[93m",
|
||||
f"[{params['branding']}Model] \033[94mAPI TTS Loading\033[0m {params['tts_model_name']} \033[94minto\033[93m",
|
||||
device,
|
||||
"\033[0m",
|
||||
)
|
||||
@@ -158,8 +158,8 @@ async def setup():
|
||||
print(
|
||||
f"[{params['branding']}Model] \033[94mModel Loaded in \033[93m{generate_elapsed_time:.2f} seconds.\033[0m"
|
||||
)
|
||||
# Set "model_loaded" to true
|
||||
params["model_loaded"] = True
|
||||
# Set "tts_model_loaded" to true
|
||||
params["tts_model_loaded"] = True
|
||||
# Set the output path for wav files
|
||||
Path(f'{params["output_folder_wav"]}').mkdir(parents=True, exist_ok=True)
|
||||
|
||||
@@ -167,7 +167,7 @@ async def setup():
|
||||
# MODEL LOADER For "API TTS"
|
||||
async def api_load_model():
|
||||
global model
|
||||
model = TTS(params["model_name"]).to(device)
|
||||
model = TTS(params["tts_model_name"]).to(device)
|
||||
return model
|
||||
|
||||
|
||||
@@ -227,7 +227,7 @@ async def unload_model(model):
|
||||
del model
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
params["model_loaded"] = False
|
||||
params["tts_model_loaded"] = False
|
||||
return None
|
||||
|
||||
|
||||
@@ -520,7 +520,7 @@ templates = Jinja2Templates(directory=this_dir / "templates")
|
||||
|
||||
# Create a dependency to get the current JSON data
|
||||
def get_json_data():
|
||||
with open(this_dir / "config.json", "r") as json_file:
|
||||
with open(this_dir / "confignew.json", "r") as json_file:
|
||||
data = json.load(json_file)
|
||||
return data
|
||||
|
||||
@@ -555,8 +555,8 @@ async def update_settings(
|
||||
local_temperature: str = Form(...),
|
||||
local_repetition_penalty: str = Form(...),
|
||||
low_vram: bool = Form(...),
|
||||
model_loaded: bool = Form(...),
|
||||
model_name: str = Form(...),
|
||||
tts_model_loaded: bool = Form(...),
|
||||
tts_model_name: str = Form(...),
|
||||
narrator_enabled: bool = Form(...),
|
||||
narrator_voice: str = Form(...),
|
||||
output_folder_wav: str = Form(...),
|
||||
@@ -577,8 +577,8 @@ async def update_settings(
|
||||
data["local_temperature"] = local_temperature
|
||||
data["local_repetition_penalty"] = local_repetition_penalty
|
||||
data["low_vram"] = low_vram
|
||||
data["model_loaded"] = model_loaded
|
||||
data["model_name"] = model_name
|
||||
data["tts_model_loaded"] = tts_model_loaded
|
||||
data["tts_model_name"] = tts_model_name
|
||||
data["narrator_enabled"] = narrator_enabled
|
||||
data["narrator_voice"] = narrator_voice
|
||||
data["output_folder_wav"] = output_folder_wav
|
||||
@@ -591,7 +591,7 @@ async def update_settings(
|
||||
data["voice"] = voice
|
||||
|
||||
# Save the updated settings back to the JSON file
|
||||
with open(this_dir / "config.json", "w") as json_file:
|
||||
with open(this_dir / "confignew.json", "w") as json_file:
|
||||
json.dump(data, json_file)
|
||||
|
||||
# Redirect to the settings page to display the updated settings
|
||||
@@ -784,7 +784,7 @@ simple_webpage = """
|
||||
<body>
|
||||
<h1 id="toc">AllTalk TTS for Text generation webUI</h1>
|
||||
<p><b>Text generation webUI</b> webpage <a href="http://{{ params["ip_address"] }}:7860" target="_blank">here</a> and documentation <a href="https://github.com/oobabooga/text-generation-webui/wiki" target="_blank">here</a></p>
|
||||
<p><b>AllTalk Github</b> <a href="https://github.com/erew123/alltalk_tts" target="_blank">here</a>
|
||||
<p><b>AllTalk Github</b> <a href="https://github.com/erew123/alltalk_tts" target="_blank">here</a>
|
||||
|
||||
<iframe src="http://{{ params["ip_address"] }}:{{ params["port_number"] }}/settings" width="100%" height="500" frameborder="0" style="margin: 0; padding: 0;"></iframe>
|
||||
|
||||
@@ -815,6 +815,9 @@ simple_webpage = """
|
||||
<p><b>IMPORTANT Note:</b> Ensure that your RP character card has asterisks around anything for the narration and double quotes around anything spoken. There is a complication ONLY with the greeting card so, ensuring it has the correct use of quotes and asterisks will help make sure that the greeting card sounds correct. I will aim to address this issue in a future update.</p>
|
||||
<p>Details on how to edit your greeting card, and where I'm at with solving this, can be found here <a href="https://github.com/erew123/alltalk_tts/tree/main#the-one-thing-i-cant-easily-work-around" target="_blank">erew123's Github</a> and you can look here at an example of how text should be formatted with quotes and asterisks <a href="#text-not-inside">Text Not inside function</a></p>
|
||||
|
||||
<p><b>AllTalk Updating instructions</b> <a href="https://github.com/erew123/alltalk_tts?#-updating" target="_blank">here</a>
|
||||
<p><b>AllTalk Help and issues</b> <a href="https://github.com/erew123/alltalk_tts?#-help-with-problems" target="_blank">here</a>
|
||||
|
||||
<h3 id="server-information">Server Information</h3>
|
||||
<ul>
|
||||
<li>Base URL: <code>http://{{ params["ip_address"] }}:{{ params["port_number"] }}</code></li>
|
||||
@@ -914,7 +917,7 @@ simple_webpage = """
|
||||
|
||||
<p>The temperature has been set at 0.70 here though, as it often produces a slightly better result (in my estimation).</p>
|
||||
|
||||
<p>The default settings for any model are usually provided in the config.json file that comes wtih the model and this file can be found within the folder where the model is stored.</p>
|
||||
<p>The default settings for any model are usually provided in the confignew.json file that comes wtih the model and this file can be found within the folder where the model is stored.</p>
|
||||
<p>These default values are carefully chosen to offer a reasonable starting point for users, and adjustments can be made based on individual preferences and use cases. However, it's important to note that changing these settings or setting them to extremes may result in unexpected outcomes. Setting extremely high or low values, especially without a good understanding of their effects, may lead to flat-sounding output or very strange-sounding output. It's advisable to experiment with adjustments incrementally and observe the impact on the generated speech to find a balance that suits your desired outcome.</p>
|
||||
<p><a href="#toc">Back to top of page</a></p>
|
||||
|
||||
@@ -989,20 +992,20 @@ simple_webpage = """
|
||||
<p>Currently/Officially only DeepSpeed v8.3 is installing on Windows, due to the broken installation routine by Microsoft, however, between myself and <a href="https://github.com/S95Sedan" target="_blank">S95Sedan</a> its now possible to install DeepSpeed v11.1 or v11.2 on Windows.</p>
|
||||
|
||||
<h4>DeepSpeed on Windows - <span class="option-a">Option A</span></h4>
|
||||
<p>This is to use the pre built DeepSpeed v11.1 wheel file. This is quite a quick process and should work for 99% of people.</p>
|
||||
<p>This is to use the pre built DeepSpeed v11.2 wheel file. This is quite a quick process and should work for 99% of people.</p>
|
||||
|
||||
<p><strong>Note:</strong> In my tests, with this method you will <strong>not</strong> need to install the Nvidia CUDA toolkit to make this work, but AllTalk may warn you when starting DeepSpeed that it doesn't see the CUDA Toolkit; however, it works fine for TTS purposes.</p>
|
||||
|
||||
<ol>
|
||||
<li>Download the file <a href="https://drive.google.com/file/d/1PFsf6uSPY5Cb4o9VxiZ7DLv-j35L7Y41/view?usp=sharing" target="_blank">deepspeed-0.11.1+e9503fe-cp311-cp311-win_amd64.whl</a> by clicking the <strong>download</strong> icon at the top right of the screen and save the file it inside your <strong>text-generation-webui</strong> folder.</li>
|
||||
<li>Download the correct wheel version for your CUDA and Python version file <a href="https://github.com/erew123/alltalk_tts/releases/tag/deepspeed" target="_blank">from here</a> and save the file it inside your <strong>text-generation-webui</strong> folder.</li>
|
||||
|
||||
<li>At a command prompt window, move into your <strong>text-generation-webui folder</strong>, you can now start the Python environment for text-generation-webui:
|
||||
<br><code>cmd_windows.bat</code></li>
|
||||
<li>At a command prompt window, move into your <strong>text-generation-webui folder</strong>, you can now start the Python environment for text-generation-webui:<br>
|
||||
<br><code>cmd_windows.bat</code></li><br>
|
||||
|
||||
<li>With the file that you saved in the <strong>text-generation-webui folder</strong>, you now type the following:
|
||||
<br><code>pip install "deepspeed-0.11.1+e9503fe-cp311-cp311-win_amd64.whl"</code></li>
|
||||
<li>With the file that you saved in the <strong>text-generation-webui folder</strong>, you now type the following:<br>
|
||||
<br><code>pip install "deepspeed-0.11.2+<b>yourversionhere</b>-win_amd64.whl"</code></li><br>
|
||||
|
||||
<li>This should install through cleanly and you should now have DeepSpeed v11.1 installed within the Python 3.11 environment of text-generation-webui.</li>
|
||||
<li>This should install through cleanly and you should now have DeepSpeed v11.2 installed within the Python 3.11 environment of text-generation-webui.</li>
|
||||
|
||||
<li>When you start up text-generation-webui, and AllTalk starts, you should see <strong>[AllTalk Startup] DeepSpeed Detected</strong></li>
|
||||
|
||||
@@ -1138,7 +1141,7 @@ simple_webpage = """
|
||||
<p><a href="#toc">Back to top of page</a></p>
|
||||
|
||||
<h3 id="configuration-details"><strong>Configuration Details</strong></h3>
|
||||
<p>Explanation of the <b>config.json</b> file:</p>
|
||||
<p>Explanation of the <b>confignew.json</b> file:</p>
|
||||
|
||||
<code><span class="key">"activate:"</span> <span class="value">true</span>,</code><span class="key"> Used within the code, do not change.</span><br>
|
||||
<code><span class="key">"autoplay:"</span> <span class="value">true</span>,</code><span class="key"> Controls whether the TTS audio plays automatically within Text generation webUI.</span><br>
|
||||
@@ -1150,8 +1153,8 @@ simple_webpage = """
|
||||
<code><span class="key">"low_vram:"</span> <span class="value">false</span>,</code><span class="key"> Controls whether the Low VRAM option is enabled or disabled.</span><br>
|
||||
<code><span class="key">"local_temperature:"</span> <span class="value">"0.70"</span>,</code><span class="key"> Sets the temperature to use with the API Local and XTTSv2 Local methods.</span><br>
|
||||
<code><span class="key">"local_repetition_penalty:"</span> <span class="value">"10.0"</span>,</code><span class="key"> Sets the repetition penalty to use with the API Local and XTTSv2 Local methods.</span><br>
|
||||
<code><span class="key">"model_loaded:"</span> <span class="value">true</span>,</code><span class="key"> Used within the code, do not change.</span><br>
|
||||
<code><span class="key">"model_name:"</span> <span class="value">"tts_models/multilingual/multi-dataset/xtts_v2"</span>,</code><span class="key"> Specifies the model that the "API TTS" method will use for TTS generation.</span><br>
|
||||
<code><span class="key">"tts_model_loaded:"</span> <span class="value">true</span>,</code><span class="key"> Used within the code, do not change.</span><br>
|
||||
<code><span class="key">"tts_model_name:"</span> <span class="value">"tts_models/multilingual/multi-dataset/xtts_v2"</span>,</code><span class="key"> Specifies the model that the "API TTS" method will use for TTS generation.</span><br>
|
||||
<code><span class="key">"narrator_enabled:"</span> <span class="value">"female_02.wav"</span>,</code><span class="key"> Specifies the default narrator voice to use for TTS.</span><br>
|
||||
<code><span class="key">"narrator_voice:"</span> <span class="value">"false"</span>,</code><span class="key"> Enables and disables the narrator function.</span><br>
|
||||
<code><span class="key">"port_number:"</span> <span class="value">"7851"</span>,</code><span class="key"> Specifies the default port number for the web server.</span><br>
|
||||
|
||||
Reference in new issue
Block a user