CodingBillionaire commited on
Commit
f015573
·
1 Parent(s): 2d91907

Upload 5 files

Browse files
notebooks/google_collab.ipynb ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "Omt6xz6ljwIR",
7
+ "metadata": {
8
+ "colab": {
9
+ "base_uri": "https://localhost:8080/"
10
+ },
11
+ "id": "Omt6xz6ljwIR",
12
+ "outputId": "89fb352e-84a8-4d3e-b0dc-28ee9d9a3e6e"
13
+ },
14
+ "outputs": [],
15
+ "source": [
16
+ "!git clone https://github.com/rsxdalv/tts-generation-webui\n"
17
+ ]
18
+ },
19
+ {
20
+ "cell_type": "code",
21
+ "execution_count": null,
22
+ "id": "a66bf3c4",
23
+ "metadata": {},
24
+ "outputs": [],
25
+ "source": [
26
+ "import os\n",
27
+ "os.chdir(\"./tts-generation-webui\")"
28
+ ]
29
+ },
30
+ {
31
+ "cell_type": "code",
32
+ "execution_count": null,
33
+ "id": "HULYvnXTjzZX",
34
+ "metadata": {
35
+ "colab": {
36
+ "base_uri": "https://localhost:8080/"
37
+ },
38
+ "id": "HULYvnXTjzZX",
39
+ "outputId": "56cd665f-a6b5-4565-ddbc-7c59053d4e4b"
40
+ },
41
+ "outputs": [],
42
+ "source": [
43
+ "# Run install/updates\n",
44
+ "!git pull\n",
45
+ "!pip install -r requirements.txt\n",
46
+ "!python update.py"
47
+ ]
48
+ },
49
+ {
50
+ "cell_type": "code",
51
+ "execution_count": null,
52
+ "id": "203e8384",
53
+ "metadata": {},
54
+ "outputs": [],
55
+ "source": [
56
+ "# Fix for deepspeed for tortoise\n",
57
+ "# pip uninstall deepspeed\n",
58
+ "# pip install deepspeed==0.8.3"
59
+ ]
60
+ },
61
+ {
62
+ "cell_type": "code",
63
+ "execution_count": null,
64
+ "id": "7726b943",
65
+ "metadata": {},
66
+ "outputs": [],
67
+ "source": [
68
+ "# Fix torchvision for MusicGen \n",
69
+ "# !pip install torchvision==0.15.0+cu117 --extra-index-url https://download.pytorch.org/whl/cu117"
70
+ ]
71
+ },
72
+ {
73
+ "cell_type": "code",
74
+ "execution_count": null,
75
+ "id": "r0FihjXLklZG",
76
+ "metadata": {
77
+ "colab": {
78
+ "base_uri": "https://localhost:8080/"
79
+ },
80
+ "id": "r0FihjXLklZG",
81
+ "outputId": "77b5030b-2d12-4c20-ab0d-970b53b9ac08"
82
+ },
83
+ "outputs": [],
84
+ "source": [
85
+ "!python server.py --share"
86
+ ]
87
+ }
88
+ ],
89
+ "metadata": {
90
+ "colab": {
91
+ "provenance": []
92
+ },
93
+ "kernelspec": {
94
+ "display_name": "Python 3",
95
+ "language": "python",
96
+ "name": "python3"
97
+ },
98
+ "language_info": {
99
+ "codemirror_mode": {
100
+ "name": "ipython",
101
+ "version": 3
102
+ },
103
+ "file_extension": ".py",
104
+ "mimetype": "text/x-python",
105
+ "name": "python",
106
+ "nbconvert_exporter": "python",
107
+ "pygments_lexer": "ipython3",
108
+ "version": "3.10.11"
109
+ }
110
+ },
111
+ "nbformat": 4,
112
+ "nbformat_minor": 5
113
+ }
notebooks/samples/konichihaaaaaaaaaa.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950fe16b48f68fa33f77be7c65540111bbdf29e255379ac6d0d8762e5fc83776
3
+ size 14980
notebooks/samples/konichihaaaaaaaaaa.wav ADDED
Binary file (170 kB). View file
 
notebooks/vocos.ipynb ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "0ba083d2",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import torch\n",
11
+ "from vocos import Vocos\n",
12
+ "import torchaudio\n",
13
+ "\n",
14
+ "vocos = Vocos.from_pretrained(\"charactr/vocos-encodec-24khz\")\n",
15
+ "\n",
16
+ "bandwidth_id = torch.tensor([3]) # 12 kbps\n",
17
+ "\n",
18
+ "y, sr = torchaudio.load(\"./samples/konichihaaaaaaaaaa.wav\")\n",
19
+ "if y.size(0) > 1: # mix to mono\n",
20
+ " y = y.mean(dim=0, keepdim=True)\n",
21
+ "y = torchaudio.functional.resample(y, orig_freq=sr, new_freq=24000)\n",
22
+ "\n",
23
+ "with torch.no_grad():\n",
24
+ " y_hat = vocos(y, bandwidth_id=bandwidth_id)\n",
25
+ "\n",
26
+ "torchaudio.save(\"samples/rap_base_vocos.wav\", y_hat, 24000)\n",
27
+ "\n",
28
+ "import IPython.display as ipd\n",
29
+ "ipd.Audio(\"samples/rap_base_vocos.wav\")"
30
+ ]
31
+ }
32
+ ],
33
+ "metadata": {
34
+ "kernelspec": {
35
+ "display_name": "Python 3",
36
+ "language": "python",
37
+ "name": "python3"
38
+ },
39
+ "language_info": {
40
+ "codemirror_mode": {
41
+ "name": "ipython",
42
+ "version": 3
43
+ },
44
+ "file_extension": ".py",
45
+ "mimetype": "text/x-python",
46
+ "name": "python",
47
+ "nbconvert_exporter": "python",
48
+ "pygments_lexer": "ipython3",
49
+ "version": "3.10.11"
50
+ }
51
+ },
52
+ "nbformat": 4,
53
+ "nbformat_minor": 5
54
+ }
outputs-rvc/.gitkeep ADDED
File without changes