lucataco/pheme 🔢❓📝 → 🖼️

Lightning automatically upgraded your loaded checkpoint from v1.2.7 to v2.1.2. To apply the upgrade to your files permanently, run `python -m pytorch_lightning.utilities.upgrade_checkpoint checkpoints/models--pyannote--embedding/snapshots/c6335d8f1cd77b30084387468a6cf26fea90009b/pytorch_model.bin`
Model was trained with pyannote.audio 0.0.1, yours is 3.1.1. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.8.1+cu102, yours is 2.1.1+cu121. Bad things might happen unless you revert torch to 1.x.
Lightning automatically upgraded your loaded checkpoint from v1.2.7 to v2.1.2. To apply the upgrade to your files permanently, run `python -m pytorch_lightning.utilities.upgrade_checkpoint checkpoints/models--pyannote--embedding/snapshots/c6335d8f1cd77b30084387468a6cf26fea90009b/pytorch_model.bin`
Model was trained with pyannote.audio 0.0.1, yours is 3.1.1. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.8.1+cu102, yours is 2.1.1+cu121. Bad things might happen unless you revert torch to 1.x.
decoder_input_ids: tensor([[   1,    3,  387,  387,  301,  492,  376,  158,  127,  660,  629,  261,
27,  751,  682,  930, 1005, 1005,  563,  957,  601,  530,  530,  484,
484,  779,  210,  210,  927,  816,   79,  794,  109,  316,  316,  316,
115,   21,  836,  603,  603,  283,  826,  253,  107,  276,  276,  276,
276,  276,  276,  195,  394,  350,   82,   82,   82,   82,  570,  570,
570,  996,  996,  996,  996,  996,  820,  820,  313,  228,  228,   79,
79,  794,  994,   19,   64,  100,  100,  169,  669,  883,  883,  102,
102,  722,  942,  942,  930,  235,  235,  563,  889,  889,  785,  288,
288,  288,  288,  288,  957,  601,  740,  740,  172,  172,  497,  318,
318, 1032, 1032,  567,  567,  614,  200,  629,  229,  229,  985,  932,
232,  187,  209,  209,  488,  488,  488,  488,  512,  512,  512,  512,
790,  790,  800,  630,  836,  722, 1000,   40,   40,   55,   78,  356,
105,  105,  105,  105,  105,  342,  139,  248,  832,  832,  321,  929,
275,  275,  185,  185,  333,  333,  246,  242,  494,  126,  231,  231,
434,  646,  832,  832,  565,  565,  721,  146,  146,  512,  512,  685,
800,  630,  289,  289,  937,  792,  950,  950,  125,  125,   61,   61,
811,  235,  235,  621,  278,  452,  598,  320,  110,  840,   64,  579,
803,  696,  503,  603,  603,  283,  283,  283,  283,  283,  857,   87,
87,   43,  229,  859,  931,  931,  356,  356,  761,  761,  761,  244,
325,  463,  463,  463,  463,  223,  223,  596,  596,  502,  502,  256,
256,  834,  616,  223,  596,  596,  550,  333,  772,  996,  820,  531,
678,  147,  546,  653,  626,  721, 1024, 1024,  925,  623,  437,  302,
1032,  605,  144,  323,  323,  323,  682,  930,  235,  726,  200, 1006,
392,   96,   96,  120,  534,  564,  564,  282,  282,  626,  764,  764,
364,  624,  111,  805,  396,  396,  850,  237,  436,  432,  432,  676,
676,  676,  415,  415,  388,  388,  764,  764,  764,  412,  412,  412,
233,  233,  499,  499,   61,   61,  759,  841,  441,  836,  269,  603,
1000,  253,  253,  877,  877,  877,  482,  482,  315,  895,  731,  731,
153,  457,  937,  962,  462,  779,  210,  887,  887,  179,  229,  850,
494,  126,  875,  231,  605,  749, 1033,  969,  969,  409,  409,  648,
175,  296,  296,  869,  692,  692,  455,  168,  997,  354,  354,  585,
241,  241,  492,  492]], device='cuda:0')
semantic_tokens: 1.3835923671722412
acoustic_tokens: 0.520693302154541
vocoder time: 0.03781533241271973