Created
October 17, 2022 07:28
-
-
Save stealthinu/8d773cce05c81c2134af52176400fdf0 to your computer and use it in GitHub Desktop.
soft-vc-test
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import torch, torchaudio\n", | |
"import IPython.display as display\n", | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"import torch.nn.functional as nnf" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"hubert = torch.hub.load(\"bshall/hubert:main\", \"hubert_soft\").cuda()\n", | |
"hubert_discrete = torch.hub.load(\"bshall/hubert:main\", \"hubert_discrete\").cuda()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"source, sr = torchaudio.load(\"dataset/textful/00_myvoice/wav/emotion002.wav\")\n", | |
"sample_rate = 16000\n", | |
"source = torchaudio.functional.resample(source, sr, sample_rate)\n", | |
"effects = [\n", | |
" ['gain', '-6.0'],\n", | |
" ['pitch', '+0'],\n", | |
" [\"rate\", f\"{sample_rate}\"]\n", | |
"]\n", | |
"source_effected = torchaudio.sox_effects.apply_effects_tensor(source, sample_rate, effects)[0]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"display.Audio(source_effected.squeeze().cpu(), rate=16000)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"with torch.inference_mode():\n", | |
" # Extract speech units\n", | |
" #units = hubert.units(source[:, :, :640+320+320]) # 320*4 -> 4\n", | |
" #units = hubert.units(source[:, :, :320]) # 最低 320 必要\n", | |
" units = hubert.units(source.unsqueeze(0).cuda())\n", | |
" #discrete = hubert_discrete.units(source.unsqueeze(0).cuda())\n", | |
" units_effected = hubert.units(source_effected.unsqueeze(0).cuda())\n", | |
" #discrete_effected = hubert_discrete.units(source_effected.unsqueeze(0).cuda())\n", | |
"diffs = units - units_effected\n", | |
"units.size()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"plt.imshow(units.transpose(1, 2).squeeze().cpu().numpy(), cmap=\"bwr\")\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"plt.imshow(units_effected.transpose(1, 2).squeeze().cpu().numpy(), cmap=\"bwr\")\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"plt.imshow(diffs.transpose(1, 2).squeeze().cpu().numpy(), cmap=\"bwr\")\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"spec_sampling_rate = 16000 / 128\n", | |
"hubert_sampling_rate = 16000 / 320\n", | |
"hubert_to_spec_rate = spec_sampling_rate / hubert_sampling_rate\n", | |
"spec_size = int(units.size(2) * hubert_to_spec_rate)\n", | |
"print(spec_sampling_rate, hubert_sampling_rate, hubert_to_spec_rate, units.size(2), spec_size)\n", | |
"\n", | |
"units_fixed = nnf.interpolate(units.transpose(1, 2), size=(spec_size), mode='linear', align_corners=False) # 'nearest' | 'linear'" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"plt.plot(units.transpose(1, 2)[0, 1].cpu().numpy())\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"plt.plot(units_fixed[0, 1].cpu().numpy())\n", | |
"plt.show()" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3.8.13 ('mmvcwsl')", | |
"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": "3.8.13" | |
}, | |
"orig_nbformat": 4, | |
"vscode": { | |
"interpreter": { | |
"hash": "ff3fdd7d80781b2f52ba823c7a1b36dbda0bf9834fe188ef410bc9fe62fc2ef7" | |
} | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment