-
See fix for Hubert here: https://github.com/kickstartDS/dr-hubert-website/commit/10b06df12f03aaa9726882905ccf0a8cc76bb628
Needs to also be added to:
- [x] Cooper
- [x] Connecta
- [x] ruhmesmeile…
-
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(…
-
train_path: ["/home/lxf/Documents/xinfeng/research/token_spoof/CodecBased/ASVSpoof2019-TSV/train.tsv", "/home/lxf/Documents/xinfeng/datasets/ASVSpoof2019/LA/ASVspoof2019_LA_cm_protocols/ASVspoof2019.L…
-
### System Info
- `transformers` version: 4.44.2
- Platform: Linux-4.18.0-477.27.1.el8_8.x86_64-x86_64-with-glibc2.28
- Python version: 3.11.9
- Huggingface_hub version: 0.23.4
- Safetensors vers…
-
```
storeHooks.ts:111 Warning: Cannot update a component (`RealAssetRow2`) while rendering a different component (`AssetsTable`). To locate the bad setState() call inside `AssetsTable`, follow the st…
-
python process.py I:\GitHub\Ultralight-Digital-Human\aa54ca97a40d02e3ad25966870b7753a.mp4 --asr hubert
[INFO] ===== extract audio from I:\GitHub\Ultralight-Digital-Human\aa54ca97a40d02e3ad25966870b7…
-
I'm training a Hubert model from scratch on 8k Hz audio speech data same as described on the paper, first iteration succeeded. I've started the second iteration where first iteration features were us…
-
The VITS project contains posterior encoder which converts audio to latent space variables.
But HuBERT does the same.
Does RVC work by generating latent space variables with HuBert and than use i…
-
看了facebook/hubert-large-ls960-ft是针对英文训练的，所以替换成TencentGameMate/chinese-hubert-large这个模型，是专门针对中文训练的模型，结果跑出来还是不理想
-
## What is your question?
I try to reproduce the results with 100h finetune data. But my final results is not so good, wer of test-clean/test-other=8.2300 / 17.3509
## training details
### First it…