-
Hi,
When I try to run step 1s -- dataset formatting -- I get the following error:
```
vocal_Saya.wav.reformatted.wav_10.flac_0022832960_0022952000.wav
vocal_Saya.wav.reformatted.wav_10.flac_0022…
-
## 用 Windows 整合包直接运行
前面所有步骤都做好了，只要一开启SoVITS训练就固定报错：
```
"D:\GitHub\GPT-SoVITS-v2-240821\runtime\python.exe" GPT_SoVITS/s2_train.py --config "D:\GitHub\GPT-SoVITS-v2-240821\TEMP/tmp_s2.json"
Traceb…
-
修复：
D:\GPT-SoVITS-v2-240821\GPT_SoVITS\prepare_datasets\2-get-hubert-wav32k.py
替换以下函数：
```
def name2go(wav_name, wav_path):
hubert_path = f"{hubert_dir}/{wav_name}.pt"
if os.path.exists(…
-
训练gpt时无论显存多少都会爆，不管batch_size设置为多少都是。
可以开始训练，中途时会报错。
音频未切分，最长38s。
```
raceback (most recent call last):
File "C:\GPT-SoVITS-v2-240821\GPT_SoVITS\s1_train.py", line 183, in
main(args)
Fi…
-
"/Users/llh/Desktop/AI/GPT-SoVITS/runtime/bin/python3" GPT_SoVITS/prepare_datasets/3-get-semantic.py
"/Users/llh/Desktop/AI/GPT-SoVITS/runtime/bin/python3" GPT_SoVITS/prepare_datasets/3-get-semantic.…
-
"D:\GPT-SoVITS-v2-240821\runtime\python.exe" GPT_SoVITS/s2_train.py --config "D:\GPT-SoVITS-v2-240821\TEMP/tmp_s2.json"
[E C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\d…
-
Chinese is a unique language. When I want to train and process with other languages, such as Vietnamese, Spanish, or Lao, do I need to change the data processing method? Specifically, the function 'co…
-
GPT训练时报错信息
"D:\GPT-SoVITS\runtime\python.exe" GPT_SoVITS/s1_train.py --config_file "D:\GPT-SoVITS\TEMP/tmp_s1.yaml"
Traceback (most recent call last):
File "D:\GPT-SoVITS\GPT_SoVITS\s1_train.py…
-
I've been using GPT-Sovits for my TTS; However, I'm running into some issues. The processing speeds which can be slow at around 2-5 iterations per second. But then, out of nowhere, it will suddenly ju…
-
启动命令：
`python api_v2.py -a 0.0.0.0 -p 7860 -c GPT_SoVITS/configs/tts_infer.yaml`
tts_infer.yaml:
`
custom:
bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
cnh…