Loading XTTS v2...
/home/ubuntu/.local/lib/python3.10/site-packages/TTS/api.py:70: UserWarning: `gpu` will be deprecated. Please use `tts.to(device)` instead.
  warnings.warn("`gpu` will be deprecated. Please use `tts.to(device)` instead.")
 > tts_models/multilingual/multi-dataset/xtts_v2 has been updated, clearing model cache...
 > You must confirm the following:
 | > "I have purchased a commercial license from Coqui: licensing@coqui.ai"
 | > "Otherwise, I agree to the terms of the non-commercial CPML: https://coqui.ai/cpml" - [y/n]
 > Downloading model to /home/ubuntu/.local/share/tts/tts_models--multilingual--multi-dataset--xtts_v2

  0%|          | 0.00/1.87G [00:00<?, ?iB/s]
  1%|          | 10.3M/1.87G [00:00<00:18, 103MiB/s]
  1%|          | 22.6M/1.87G [00:00<00:16, 115MiB/s]
  2%|▏         | 35.1M/1.87G [00:00<00:15, 120MiB/s]
  3%|▎         | 47.6M/1.87G [00:00<00:14, 122MiB/s]
  3%|▎         | 60.1M/1.87G [00:00<00:14, 123MiB/s]
  4%|▍         | 72.4M/1.87G [00:00<00:14, 122MiB/s]
  5%|▍         | 84.8M/1.87G [00:00<00:14, 123MiB/s]
  5%|▌         | 97.3M/1.87G [00:00<00:14, 123MiB/s]
  6%|▌         | 110M/1.87G [00:00<00:14, 124MiB/s] 
  7%|▋         | 122M/1.87G [00:01<00:14, 124MiB/s]
  7%|▋         | 134M/1.87G [00:01<00:14, 124MiB/s]
  8%|▊         | 147M/1.87G [00:01<00:13, 124MiB/s]
  9%|▊         | 159M/1.87G [00:01<00:13, 124MiB/s]
  9%|▉         | 172M/1.87G [00:01<00:13, 124MiB/s]
 10%|▉         | 184M/1.87G [00:01<00:13, 124MiB/s]
 11%|█         | 197M/1.87G [00:01<00:13, 124MiB/s]
 11%|█         | 209M/1.87G [00:01<00:13, 125MiB/s]
 12%|█▏        | 222M/1.87G [00:01<00:13, 125MiB/s]
 13%|█▎        | 234M/1.87G [00:01<00:13, 125MiB/s]
 13%|█▎        | 247M/1.87G [00:02<00:13, 124MiB/s]
 14%|█▍        | 259M/1.87G [00:02<00:12, 125MiB/s]
 15%|█▍        | 272M/1.87G [00:02<00:12, 125MiB/s]
 15%|█▌        | 284M/1.87G [00:02<00:12, 125MiB/s]
 16%|█▌        | 297M/1.87G [00:02<00:12, 123MiB/s]
 17%|█▋        | 309M/1.87G [00:02<00:12, 123MiB/s]
 17%|█▋        | 322M/1.87G [00:02<00:12, 124MiB/s]
 18%|█▊        | 334M/1.87G [00:02<00:12, 124MiB/s]
 19%|█▊        | 347M/1.87G [00:02<00:12, 124MiB/s]
 19%|█▉        | 359M/1.87G [00:02<00:12, 125MiB/s]
 20%|█▉        | 372M/1.87G [00:03<00:11, 125MiB/s]
 21%|██        | 384M/1.87G [00:03<00:11, 125MiB/s]
 21%|██        | 397M/1.87G [00:03<00:11, 125MiB/s]
 22%|██▏       | 409M/1.87G [00:03<00:11, 125MiB/s]
 23%|██▎       | 422M/1.87G [00:03<00:11, 124MiB/s]
 23%|██▎       | 434M/1.87G [00:03<00:11, 125MiB/s]
 24%|██▍       | 447M/1.87G [00:03<00:11, 124MiB/s]
 25%|██▍       | 459M/1.87G [00:03<00:11, 124MiB/s]
 25%|██▌       | 471M/1.87G [00:03<00:11, 124MiB/s]
 26%|██▌       | 484M/1.87G [00:03<00:11, 124MiB/s]
 27%|██▋       | 496M/1.87G [00:04<00:11, 124MiB/s]
 27%|██▋       | 509M/1.87G [00:04<00:11, 120MiB/s]
 28%|██▊       | 521M/1.87G [00:04<00:11, 121MiB/s]
 29%|██▊       | 534M/1.87G [00:04<00:10, 122MiB/s]
 29%|██▉       | 546M/1.87G [00:04<00:10, 123MiB/s]
 30%|██▉       | 559M/1.87G [00:04<00:10, 124MiB/s]
 31%|███       | 571M/1.87G [00:04<00:10, 124MiB/s]
 31%|███       | 583M/1.87G [00:04<00:10, 124MiB/s]
 32%|███▏      | 596M/1.87G [00:04<00:10, 124MiB/s]
 33%|███▎      | 608M/1.87G [00:04<00:10, 124MiB/s]
 33%|███▎      | 621M/1.87G [00:05<00:10, 124MiB/s]
 34%|███▍      | 633M/1.87G [00:05<00:09, 124MiB/s]
 35%|███▍      | 645M/1.87G [00:05<00:09, 124MiB/s]
 35%|███▌      | 658M/1.87G [00:05<00:09, 124MiB/s]
 36%|███▌      | 670M/1.87G [00:05<00:09, 124MiB/s]
 37%|███▋      | 683M/1.87G [00:05<00:09, 124MiB/s]
 37%|███▋      | 695M/1.87G [00:05<00:09, 124MiB/s]
 38%|███▊      | 708M/1.87G [00:05<00:09, 124MiB/s]
 39%|███▊      | 720M/1.87G [00:05<00:09, 124MiB/s]
 39%|███▉      | 732M/1.87G [00:05<00:09, 124MiB/s]
 40%|███▉      | 745M/1.87G [00:06<00:09, 124MiB/s]
 41%|████      | 757M/1.87G [00:06<00:08, 125MiB/s]
 41%|████      | 770M/1.87G [00:06<00:08, 125MiB/s]
 42%|████▏     | 782M/1.87G [00:06<00:08, 125MiB/s]
 43%|████▎     | 795M/1.87G [00:06<00:08, 125MiB/s]
 43%|████▎     | 807M/1.87G [00:06<00:08, 125MiB/s]
 44%|████▍     | 820M/1.87G [00:06<00:08, 124MiB/s]
 45%|████▍     | 832M/1.87G [00:06<00:08, 124MiB/s]
 45%|████▌     | 845M/1.87G [00:06<00:08, 124MiB/s]
 46%|████▌     | 857M/1.87G [00:06<00:08, 124MiB/s]
 47%|████▋     | 870M/1.87G [00:07<00:08, 124MiB/s]
 47%|████▋     | 882M/1.87G [00:07<00:07, 124MiB/s]
 48%|████▊     | 895M/1.87G [00:07<00:07, 124MiB/s]
 49%|████▊     | 907M/1.87G [00:07<00:07, 124MiB/s]
 49%|████▉     | 920M/1.87G [00:07<00:07, 125MiB/s]
 50%|████▉     | 932M/1.87G [00:07<00:07, 125MiB/s]
 51%|█████     | 945M/1.87G [00:07<00:07, 125MiB/s]
 51%|█████     | 957M/1.87G [00:07<00:07, 125MiB/s]
 52%|█████▏    | 970M/1.87G [00:07<00:07, 125MiB/s]
 53%|█████▎    | 982M/1.87G [00:07<00:07, 125MiB/s]
 53%|█████▎    | 995M/1.87G [00:08<00:06, 125MiB/s]
 54%|█████▍    | 1.01G/1.87G [00:08<00:06, 125MiB/s]
 55%|█████▍    | 1.02G/1.87G [00:08<00:06, 125MiB/s]
 55%|█████▌    | 1.03G/1.87G [00:08<00:06, 124MiB/s]
 56%|█████▌    | 1.04G/1.87G [00:08<00:06, 125MiB/s]
 57%|█████▋    | 1.06G/1.87G [00:08<00:06, 125MiB/s]
 57%|█████▋    | 1.07G/1.87G [00:08<00:06, 125MiB/s]
 58%|█████▊    | 1.08G/1.87G [00:08<00:06, 124MiB/s]
 59%|█████▊    | 1.09G/1.87G [00:08<00:06, 124MiB/s]
 59%|█████▉    | 1.11G/1.87G [00:08<00:06, 124MiB/s]
 60%|█████▉    | 1.12G/1.87G [00:09<00:06, 124MiB/s]
 61%|██████    | 1.13G/1.87G [00:09<00:05, 124MiB/s]
 61%|██████▏   | 1.14G/1.87G [00:09<00:05, 124MiB/s]
 62%|██████▏   | 1.16G/1.87G [00:09<00:05, 124MiB/s]
 63%|██████▎   | 1.17G/1.87G [00:09<00:05, 124MiB/s]
 63%|██████▎   | 1.18G/1.87G [00:09<00:05, 124MiB/s]
 64%|██████▍   | 1.19G/1.87G [00:09<00:05, 124MiB/s]
 65%|██████▍   | 1.21G/1.87G [00:09<00:05, 124MiB/s]
 65%|██████▌   | 1.22G/1.87G [00:09<00:05, 124MiB/s]
 66%|██████▌   | 1.23G/1.87G [00:09<00:05, 124MiB/s]
 67%|██████▋   | 1.24G/1.87G [00:10<00:05, 124MiB/s]
 67%|██████▋   | 1.26G/1.87G [00:10<00:04, 124MiB/s]
 68%|██████▊   | 1.27G/1.87G [00:10<00:04, 123MiB/s]
 69%|██████▊   | 1.28G/1.87G [00:10<00:04, 124MiB/s]
 69%|██████▉   | 1.29G/1.87G [00:10<00:04, 124MiB/s]
 70%|██████▉   | 1.31G/1.87G [00:10<00:04, 122MiB/s]
 71%|███████   | 1.32G/1.87G [00:10<00:04, 119MiB/s]
 71%|███████   | 1.33G/1.87G [00:10<00:04, 117MiB/s]
 72%|███████▏  | 1.34G/1.87G [00:10<00:04, 116MiB/s]
 72%|███████▏  | 1.35G/1.87G [00:10<00:04, 117MiB/s]
 73%|███████▎  | 1.37G/1.87G [00:11<00:04, 119MiB/s]
 74%|███████▍  | 1.38G/1.87G [00:11<00:04, 120MiB/s]
 74%|███████▍  | 1.39G/1.87G [00:11<00:03, 121MiB/s]
 75%|███████▌  | 1.40G/1.87G [00:11<00:03, 122MiB/s]
 76%|███████▌  | 1.41G/1.87G [00:11<00:03, 123MiB/s]
 76%|███████▋  | 1.43G/1.87G [00:11<00:03, 123MiB/s]
 77%|███████▋  | 1.44G/1.87G [00:11<00:05, 78.5MiB/s]
 78%|███████▊  | 1.45G/1.87G [00:11<00:04, 88.1MiB/s]
 78%|███████▊  | 1.46G/1.87G [00:12<00:04, 96.1MiB/s]
 79%|███████▉  | 1.48G/1.87G [00:12<00:03, 103MiB/s] 
 80%|███████▉  | 1.49G/1.87G [00:12<00:03, 108MiB/s]
 80%|████████  | 1.50G/1.87G [00:12<00:03, 112MiB/s]
 81%|████████  | 1.51G/1.87G [00:12<00:03, 115MiB/s]
 82%|████████▏ | 1.53G/1.87G [00:12<00:02, 117MiB/s]
 82%|████████▏ | 1.54G/1.87G [00:12<00:02, 119MiB/s]
 83%|████████▎ | 1.55G/1.87G [00:12<00:02, 120MiB/s]
 84%|████████▎ | 1.56G/1.87G [00:12<00:02, 121MiB/s]
 84%|████████▍ | 1.57G/1.87G [00:12<00:02, 122MiB/s]
 85%|████████▍ | 1.59G/1.87G [00:13<00:02, 122MiB/s]
 86%|████████▌ | 1.60G/1.87G [00:13<00:02, 122MiB/s]
 86%|████████▋ | 1.61G/1.87G [00:13<00:02, 123MiB/s]
 87%|████████▋ | 1.62G/1.87G [00:13<00:01, 123MiB/s]
 88%|████████▊ | 1.64G/1.87G [00:13<00:01, 123MiB/s]
 88%|████████▊ | 1.65G/1.87G [00:13<00:01, 123MiB/s]
 89%|████████▉ | 1.66G/1.87G [00:13<00:01, 123MiB/s]
 90%|████████▉ | 1.67G/1.87G [00:13<00:01, 123MiB/s]
 90%|█████████ | 1.69G/1.87G [00:13<00:01, 123MiB/s]
 91%|█████████ | 1.70G/1.87G [00:13<00:01, 122MiB/s]
 92%|█████████▏| 1.71G/1.87G [00:14<00:01, 123MiB/s]
 92%|█████████▏| 1.72G/1.87G [00:14<00:01, 123MiB/s]
 93%|█████████▎| 1.73G/1.87G [00:14<00:01, 122MiB/s]
 94%|█████████▎| 1.75G/1.87G [00:14<00:01, 118MiB/s]
 94%|█████████▍| 1.76G/1.87G [00:14<00:00, 120MiB/s]
 95%|█████████▍| 1.77G/1.87G [00:14<00:00, 121MiB/s]
 96%|█████████▌| 1.78G/1.87G [00:14<00:00, 121MiB/s]
 96%|█████████▌| 1.80G/1.87G [00:14<00:00, 121MiB/s]
 97%|█████████▋| 1.81G/1.87G [00:14<00:00, 122MiB/s]
 97%|█████████▋| 1.82G/1.87G [00:14<00:00, 122MiB/s]
 98%|█████████▊| 1.83G/1.87G [00:15<00:00, 123MiB/s]
 99%|█████████▉| 1.85G/1.87G [00:15<00:00, 123MiB/s]
 99%|█████████▉| 1.86G/1.87G [00:15<00:00, 123MiB/s]

0.00iB [00:00, ?iB/s]
100%|██████████| 1.87G/1.87G [00:15<00:00, 119MiB/s]

0.00iB [00:00, ?iB/s]
4.37kiB [00:00, 12.1kiB/s]


  0%|          | 0.00/32.0 [00:00<?, ?iB/s]
361kiB [00:00, 973kiB/s]

  0%|          | 0.00/7.75M [00:00<?, ?iB/s]
100%|██████████| 32.0/32.0 [00:00<00:00, 69.3iB/s]
 > Model's license - CPML
 > Check https://coqui.ai/cpml.txt for more info.
 > Using model: xtts
/home/ubuntu/.local/lib/python3.10/site-packages/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)
/home/ubuntu/.local/lib/python3.10/site-packages/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)
GPT2InferenceModel has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
WARNING:transformers.modeling_utils:GPT2InferenceModel has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
Loaded. VRAM: 1.9GB
 > Text splitted to sentences.
['warmup test.']
The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
WARNING:transformers.generation.utils:The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
 > Processing time: 1.8866982460021973
 > Real-time factor: 0.3667803668037492
Warmed up
 > Text splitted to sentences.
['मेरे प्यारे देशवासियों, आज मैं आपके साथ कुछ बहुत ज़रूरी बातें करना चाहता हूँ.', 'हमारा देश एक नये दौर में प्रवेश कर रहा है.']
 > Processing time: 4.192692518234253
 > Real-time factor: 0.3052326664918954
medium: 12.62s audio | 4.23s gen | RTF=0.335x | GPU=33%
 > Text splitted to sentences.
['भारत आज दुनिया की पाँचवीं सबसे बड़ी अर्थव्यवस्था है.', 'हमारे युवाओं की ऊर्जा, हमारे वैज्ञानिकों की प्रतिभा, और हमारे किसानों की मेहनत, यही हमारी असली ताकत है.']
 > Processing time: 5.148412704467773
 > Real-time factor: 0.30792276097320764
speech: 15.36s audio | 5.20s gen | RTF=0.338x | GPU=33%
VRAM: 1.9GB
Done. Samples in /home/ubuntu/xtts_samples/