Retrieval-based-Voice-Conversion-WebUI
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
Easily train a good VC model with voice data <= 10 mins!
日志如下 2023-05-18 13:50:10 | INFO | faiss.loader | Loading faiss with AVX2 support. 2023-05-18 13:50:10 | INFO | faiss.loader | Could not load library with AVX2 support due to: ModuleNotFoundError("No...
``` naozumi@Naozumis-MacBook-Pro RVC-beta % pip3 install faiss-cpu==1.7.0 Collecting faiss-cpu==1.7.0 Using cached faiss-cpu-1.7.0.tar.gz (34 kB) Preparing metadata (setup.py) ... done Building wheels for collected packages: faiss-cpu Building wheel for faiss-cpu (setup.py)...
 我的训练模型的时候是40Khz,V1,无音高指导...很无奈。弄了很久感觉是模型问题,我是哪里出错了吗
### More information needed ### Haven't tested on other platforms! ### Changes: 1. Using np.int64 instead of np.int in `gui.py`,`extract_f0_print.py` and `vc_infer_pipeline.py` to correspond to numpy's deprecating np.int. 2. Added...
Incorrect or incomplete translations have been corrected.
As title, I was not able to do train process under macOS. Here's the errors: ``` INFO:HoshinoAi:{'train': {'log_interval': 200, 'seed': 1234, 'epochs': 20000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09,...
 while trying to train a voice it always sends me this message
Bug
/content/Retrieval-based-Voice-Conversion-WebUI Use Language: en_US 2023-05-21 10:02:12.449487: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F FMA, in...
修復了實時語音轉換無法使用的一些簡單問題
input device:1:麦克风 (Meizu HiFi DAC Headphone A (MME) output device:5:耳机 (Meizu HiFi DAC Headphone Am (MME) {'hubert_path': 'C:/AIGC/TTS/RVC-beta/hubert_base.pt', 'pth_path': 'C:/Users/HP/Documents/RVC_paimon/paimeng/paimeng.pth', 'index_path': 'C:/Users/HP/Documents/RVC_paimon/paimeng/trained_IVF13060_Flat_nprobe_1.index', 'npy_path': 'C:/Users/HP/Documents/RVC_paimon/paimeng/total_fea.npy', 'pitch': 12.0, 'samplerate': 44100, 'block_time': 1.0,...