weary inlet
By well, I mean, this doesnt work at all right now. After uploading a model, tried to restart the server and, it is stuck on loading index. Help?
2025-05-11 14:13:46,323 INFO [main] Python: 3.10.15 (main, Sep 9 2024, 03:02:42) [GCC 9.4.0]
2025-05-11 14:13:46,324 INFO [main] Voice changer version: b2332 NVIDIA-CUDA
2025-05-11 14:13:46,324 INFO [WeightDownloader] Loading weights.
...
2025-05-11 14:13:49,751 INFO [RVCInferencerv2] Compiling JIT model...
2025-05-11 14:13:52,038 INFO [EmbedderManager] Loading embedder hubert_base
2025-05-11 14:13:53,336 INFO [PitchExtractorManager] Loading pitch extractor rmvpe_onnx
2025-05-11 14:13:54.727104002 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 2 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
2025-05-11 14:13:54,839 INFO [PipelineGenerator] Loading index...
2025-05-11 14:13:54,839 INFO [PipelineGenerator] Try loading "model_dir/0/added_IVF256_Flat_nprobe_1_FurinaEN4.2_v2.index"...
faiss/contrib/torch_utils.py:51: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
