Running on local URL: http://0.0.0.0:5003 IMPORTANT: You are using gradio version 4.25.0, however version 4.44.1 is available, please upgrade. -------- Running on public URL: https://d919144c7bc8acc011.gradio.live This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces) /content/XTTSv2-Finetuning-Vi/TTS/tts/layers/xtts/xtts_manager.py:5: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. self.speakers = torch.load(speaker_file_path) /content/XTTSv2-Finetuning-Vi/TTS/utils/io.py:54: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. return torch.load(f, map_location=map_location, **kwargs) [2024-10-22 08:47:29,710] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-10-22 08:47:31,438] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.15.2, git-hash=unknown, git-branch=unknown [2024-10-22 08:47:31,439] [WARNING] [config_utils.py:70:_process_deprecated_field] Config parameter replace_method is deprecated. This parameter is no longer needed, please remove from your call to DeepSpeed-inference [2024-10-22 08:47:31,439] [WARNING] [config_utils.py:70:_process_deprecated_field] Config parameter mp_size is deprecated use tensor_parallel.tp_size instead [2024-10-22 08:47:31,579] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1 [2024-10-22 08:47:32,569] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 1024, 'intermediate_size': 4096, 'heads': 16, 'num_hidden_layers': -1, 'dtype': torch.float32, 'pre_layer_norm': True, 'norm_type': , 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': -1, 'rotate_half': False, 'rotate_every_two': True, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': , 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000, 'invert_mask': True} Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja build file /root/.cache/torch_extensions/py310_cu121/transformer_inference/build.ninja... /usr/local/lib/python3.10/dist-packages/torch/utils/cpp_extension.py:1965: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST']. warnings.warn( Building extension module transformer_inference... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) Loading extension module transformer_inference... Time to load transformer_inference op: 0.11538887023925781 seconds Model Loaded! Running filter... Computing conditioning latents... ['Xin chào, tôi là một công cụ chuyển đổi văn bản thành giọng nói tiếng Việt ' 'được huấn luyện trong môn học xử lý giọng nói.'] Saving output to /content/XTTSv2-Finetuning-Vi/output/1022084744_xin_chao_toi_la_mot_cong_cu_chuyen_doi_van_ban_th_9971aa9a524172a6cda16d2e251ecfd2a18d05b9.wav Using filter cache... Using conditioning latents cache... ['Xin chào, tôi là một công cụ chuyển đổi văn bản thành giọng nói tiếng Việt, ' 'được huấn luyện trong môn học xử lý giọng nói.'] Saving output to /content/XTTSv2-Finetuning-Vi/output/1022084801_xin_chao_toi_la_mot_cong_cu_chuyen_doi_van_ban_th_9971aa9a524172a6cda16d2e251ecfd2a18d05b9.wav Keyboard interruption in main thread... closing server. Killing tunnel 0.0.0.0:5003 <> https://d919144c7bc8acc011.gradio.live