{
"cells": [
{
"cell_type": "code",
"execution_count": 8,
"id": "3abd2681",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:55:28.303023Z",
"start_time": "2023-08-24T15:55:28.275971Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The autoreload extension is already loaded. To reload it, use:\n",
" %reload_ext autoreload\n"
]
}
],
"source": [
"import os\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"\n",
"\n",
"from suno_utils.audio import Audio\n",
"from suno_utils.tasks.mert_v2 import (\n",
" encode as mert_encode,\n",
" preload_models as preload_mert_models\n",
")\n",
"from suno_utils.tasks.dac import (\n",
" encode as codec_encode,\n",
" decode as codec_decode,\n",
" preload_models as preload_codec_models,\n",
")\n",
"\n",
"from suno_utils.tasks.gpt_v2.chirp_v1 import preload_models as preload_chirp_models\n",
"from suno_utils.tasks.gpt_v2.chirp_v1 import generate_audio\n",
"from suno_utils.tasks.gpt_v2.generation import generate\n",
"\n",
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f97f7e06",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:55:46.018110Z",
"start_time": "2023-08-24T15:55:28.304173Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"model loaded: 1720.9M params, 1.52 loss\n"
]
}
],
"source": [
"preload_chirp_models(\n",
" centroids_filepath=\"/home/mikeys/bundle/2x1k_centroids_mert.npy\",\n",
" gpt_ckpt_path=\"/home/mikeys/bundle/xl_s5.pt\",\n",
" codec_ckpt_path=\"/home/mikeys/bundle/d_codec_25x8.pt\",\n",
" common_genre_tags_path=\"/home/mikeys/bundle/common_tags.json\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "cceb2397",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:57:37.944878Z",
"start_time": "2023-08-24T15:55:46.020391Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 94%|████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 2993/3185 [01:50<00:07, 26.97it/s]\n"
]
}
],
"source": [
"text = \"\"\"\n",
"[Verse]\n",
"花褪残红\n",
"青杏小\n",
"燕子飞时\n",
"绿水\n",
"人家绕\n",
"枝上柳绵\n",
"吹又少\n",
"\n",
"[Chorus]\n",
"天涯何处无芳草\n",
"无芳草\n",
"\"\"\"\n",
"out = generate_audio(\n",
" text,\n",
" text_tags=\"[mandopop]\", \n",
" n_batch=2,\n",
" history_audio=None,\n",
" history_text=None,\n",
" max_gen_duration_s=40,\n",
" max_history_duration_s=10.01,\n",
" temp_semantic=0.8,\n",
" temp_coarse=0.8,\n",
" top_k_semantic=250,\n",
" top_k_coarse=500,\n",
" cfg_coef=2.25,\n",
" cfg_coef_tags=1.75,\n",
" min_eos_p=0.5,\n",
" rep_penality=0.2,\n",
" allow_genre_randomization=False,\n",
" silent=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f1cbb567",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:57:39.647943Z",
"start_time": "2023-08-24T15:57:37.946131Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#codec_decode(out[1][1][0]).play()\n",
"for o in out:\n",
" o.play()\n",
"# or out[0][0].play()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "e3c7d909",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:57:39.671392Z",
"start_time": "2023-08-24T15:57:39.649079Z"
}
},
"outputs": [],
"source": [
"my_audio = out[1]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "dd1076d4",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:58:14.674225Z",
"start_time": "2023-08-24T15:57:39.672871Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 34%|████████████████████████████████████▊ | 830/2435 [00:34<01:06, 24.31it/s]\n"
]
}
],
"source": [
"text_2 = \"\"\"\n",
"[Chorus]\n",
"墙里秋千\n",
"墙外道\n",
"墙外行人\n",
"墙里\n",
"佳人笑\n",
"笑渐不闻\n",
"声渐悄\n",
"\n",
"[Beat]\n",
"多情却被无情恼\n",
"无情恼\n",
"[Beat]\n",
"\"\"\"\n",
"out_2 = generate_audio(\n",
" text_2,\n",
" text_tags=\"[kpop]\", \n",
" n_batch=2,\n",
" history_audio=my_audio,\n",
" history_text=text,\n",
" max_gen_duration_s=30,\n",
" max_history_duration_s=10.01,\n",
" temp_semantic=0.8,\n",
" temp_coarse=0.8,\n",
" top_k_semantic=250,\n",
" top_k_coarse=500,\n",
" cfg_coef=2.25,\n",
" cfg_coef_tags=1.75,\n",
" min_eos_p=0.8,\n",
" rep_penality=0.2,\n",
" allow_genre_randomization=False,\n",
" silent=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "c8705ad1",
"metadata": {
"ExecuteTime": {
"end_time": "2023-08-24T15:58:14.841203Z",
"start_time": "2023-08-24T15:58:14.675908Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"for o2 in out_2:\n",
" o2.play()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ab458636",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.12"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 5
}