Spaces:
Runtime error
Runtime error
File size: 3,652 Bytes
c021d8e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pickle\n",
"import numpy as np\n",
"import torch\n",
"import torch.nn.functional as F\n",
"from collections import OrderedDict\n",
"from onmt_modules.misc import sequence_mask\n",
"from model_autopst import Generator_2 as Predictor\n",
"from hparams_autopst import hparams\n",
"\n",
"device = 'cuda:0'\n",
"\n",
"P = Predictor(hparams).eval().to(device)\n",
"\n",
"checkpoint = torch.load('./assets/580000-P.ckpt', map_location=lambda storage, loc: storage) \n",
"P.load_state_dict(checkpoint['model'], strict=True)\n",
"print('Loaded predictor .....................................................')\n",
"\n",
"dict_test = pickle.load(open('./assets/test_vctk.meta', 'rb'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"spect_vc = OrderedDict()\n",
"\n",
"uttrs = [('p231', 'p270', '001'),\n",
" ('p270', 'p231', '001'),\n",
" ('p231', 'p245', '003001'),\n",
" ('p245', 'p231', '003001'),\n",
" ('p239', 'p270', '024002'),\n",
" ('p270', 'p239', '024002')]\n",
"\n",
"\n",
"for uttr in uttrs:\n",
" \n",
" cep_real, spk_emb = dict_test[uttr[0]][uttr[2]]\n",
" cep_real_A = torch.from_numpy(cep_real).unsqueeze(0).to(device)\n",
" len_real_A = torch.tensor(cep_real_A.size(1)).unsqueeze(0).to(device)\n",
" real_mask_A = sequence_mask(len_real_A, cep_real_A.size(1)).float()\n",
" \n",
" _, spk_emb = dict_test[uttr[1]][uttr[2]]\n",
" spk_emb_B = torch.from_numpy(spk_emb).unsqueeze(0).to(device)\n",
" \n",
" with torch.no_grad():\n",
" spect_output, len_spect = P.infer_onmt(cep_real_A.transpose(2,1)[:,:14,:],\n",
" real_mask_A,\n",
" len_real_A,\n",
" spk_emb_B)\n",
" \n",
" uttr_tgt = spect_output[:len_spect[0],0,:].cpu().numpy()\n",
" \n",
" spect_vc[f'{uttr[0]}_{uttr[1]}_{uttr[2]}'] = uttr_tgt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# spectrogram to waveform\n",
"# Feel free to use other vocoders\n",
"# This cell requires some preparation to work, please see the corresponding part in AutoVC\n",
"import torch\n",
"import librosa\n",
"import pickle\n",
"import os\n",
"from synthesis import build_model\n",
"from synthesis import wavegen\n",
"\n",
"model = build_model().to(device)\n",
"checkpoint = torch.load(\"./assets/checkpoint_step001000000_ema.pth\")\n",
"model.load_state_dict(checkpoint[\"state_dict\"])\n",
"\n",
"for name, sp in spect_vc.items():\n",
" print(name)\n",
" waveform = wavegen(model, c=sp) \n",
" librosa.output.write_wav('./assets/'+name+'.wav', waveform, sr=16000)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|