bensonbs
bensonbs
**調用 GPU 推理功能** 測試以下作法能夠成功調用GPU推理 使用 onnxruntime gpu版本 ``` pip install onnxruntime-gpu ``` 測試是否安裝成功 ``` import onnxruntime print(onnxruntime.get_device()) GPU ``` 測試是否調用成功 ``` ort_session = onnxruntime.InferenceSession("./G2PWModel-v2-onnx/g2pw.onnx",providers=['CUDAExecutionProvider']) print(ort_session.get_providers()) ['CUDAExecutionProvider', 'CPUExecutionProvider'] ``` 理論上只須修改此行 https://github.com/GitYCC/g2pW/blob/36b02d4d7058160cef8112a458aa2cdcd1c8e5bf/g2pw/api.py#L70...
``` import cv2 # read an image img = cv2.imread('cat.jpg', 1) cv2.imshow('image',img) cv2.waitKey(0) cv2.destroyAllWindows() ``` is work but add import TrackingAnything ``` from track_anything import TrackingAnything import cv2 # read...
Additionally, I want to ask why some losses increase during training. Should I choose the last checkpoint or the best checkpoint?
### Describe the bug When generating higher-pitched female voices after fine-tuning the xtts-v2 model, there is a noticeable hoarseness, resembling the strain one might experience when trying to reach high...
`tn/chinese/rules/cardinal.py` ``` # 10001111, 1001111, 101111, 11111, 10111, 10011, 10001, 10000 ten_thousand = ((thousand | hundred | ten | digit) + insert('萬') + (thousand | (zero + rmpunct + hundred)...
How to convert model to GGUF after fine-tuned?