From 993d065368385c2a03c06a1359fdb6a4b0227689 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 24 Dec 2023 18:01:27 +0000
Subject: [PATCH] Few minor updates
Couple of documentation spelling mistakes
Set environment variable
---
finetune.py | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/finetune.py b/finetune.py
index 4312c8e..9eb3e10 100644
--- a/finetune.py
+++ b/finetune.py
@@ -28,6 +28,7 @@ out_path = this_dir / "finetune" / "tmp-trn"
progress = 0
theme = gr.themes.Default()
refresh_symbol = '🔄'
+os.environ['TRAINER_TELEMETRY'] = '0'
# Define the path to the modeldownload config file file
modeldownload_config_file_path = this_dir / "modeldownload.json"
@@ -470,10 +471,10 @@ def run_tts(lang, tts_text, speaker_audio_file):
return "Speech generated !", out_path, speaker_audio_file
-def get_available_voices(minimum_size_kb=1300):
+def get_available_voices(minimum_size_kb=1200):
voice_files = [
voice for voice in Path(f"{this_dir}/finetune/tmp-trn/wavs").glob("*.wav")
- if voice.stat().st_size > minimum_size_kb * 1300 # Convert KB to bytes
+ if voice.stat().st_size > minimum_size_kb * 1200 # Convert KB to bytes
]
return sorted([str(file) for file in voice_files]) # Return full path as string
@@ -620,7 +621,7 @@ if __name__ == "__main__":
## Finetuning Information
### 🟥 Important Note
#### 🟥 finetune.py needs to be run from the /alltalk_tts/ folder. Don't move the location of this script.
- #### 🟥 Have you run AllTalk at least once? It needs to have downloaded the voice model, before we can finetune it.
+ #### 🟥 Have you run AllTalk at least once? It needs to have downloaded+updated the voice model, before we can finetune it.
### 🟦 What you need to run finetuning
#### 🟦 An Nvidia GPU. Tested on Windows with extended shared VRAM and training used about 16GB's total (which worked on a 12GB card).
#### 🟦 I have not been able to test this on a GPU with less than 12GB of VRAM, so cannot say if it will work or how that would affect performance.
@@ -839,6 +840,7 @@ if __name__ == "__main__":
## STEP 3 - Inference/Testing
### 🟥 Important Note
#### 🟥 This step will error if you are using TTS version 0.22.0. Please re-run pip install -r requirements_finetune.txt if it errors loading the model.
+ #### 🟥 If you dont see multiple speaker reference files and you used more than 3 minutes of speech, try refreshing the page as it may not have loaded them correctly.
### 🟦 What you need to do
#### 🟦 The model is now trained and you are at the testing stage. Hopefully all the dropdowns should be pre-populated now.
#### 🟦 You need to Load Fine-tuned XTTS model and then select your Speaker Reference Audio. You can choose various Speaker Reference Audios to see which works best.
@@ -941,7 +943,7 @@ if __name__ == "__main__":
### 🟦 What you need to do
#### 🟦 The wav(s) you liked from Speaker Reference Audios are in /finetune/tmp-trn/wavs/ so copy the one(s) you selected to your /alltalk_tts/voices/ samples folder.
#### 🟦 You can delete your original samples from inside of the /finetune/put-voice-samples-in-here/ folder.
- #### 🟦 In the folder /finetune/tmp-trn/training/XTTS_FT(date here)/ you will find your best_model.pth, config.json and voice.json (also the last epoch training best_model_xxx.pth)
+ #### 🟦 In the folder /finetune/tmp-trn/training/XTTS_FT(date here)/ you will find your best_model.pth, config.json and vocab.json (also the last epoch training best_model_xxx.pth)
#### 🟦 You can delete the last epoch training model file best_model_xxx.pth (the one with the numbers).
#### 🟦 You will need to rename best_model.pth to model.pth.
#### 🟦 You will close the Finetuning application and copy your 3 files listed above over the top of the existing model files inside your /alltalk_tts/models/xttsv2_2.0.2/ folder.