{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f3ac6404",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:46.776212Z",
"start_time": "2024-02-24T14:59:46.771757Z"
}
},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e59541a3",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:49.102401Z",
"start_time": "2024-02-24T14:59:46.778274Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.1.2+cu118\n",
"2.1.2+cu118\n",
"cpu\n"
]
}
],
"source": [
"import torch\n",
"import torchaudio\n",
"\n",
"print(torch.__version__)\n",
"print(torchaudio.__version__)\n",
"\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"print(device)\n",
"\n",
"from typing import List\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from torchaudio.pipelines import MMS_FA as bundle\n",
"import re\n",
"import json\n",
"from suno_utils.utils.s3 import read_from_s3, check_s3_file_exists, open_from_s3\n",
"from suno_utils.utils.text import (\n",
" write_jsonl,\n",
" read_jsonl,\n",
" write_json,\n",
" read_json,\n",
" normalize_whitespace,\n",
")\n",
"import copy\n",
"import tqdm\n",
"import numpy as np\n",
"from suno_utils.tasks.hoot import (\n",
" preload_models,\n",
" encode_filepaths,\n",
" encode,\n",
" Tokenizer,\n",
" clean_models,\n",
" load_model,\n",
" models,\n",
" ctc_align,\n",
" parse_lyrics,\n",
" decode_logits,\n",
" load_model_list,\n",
" get_aligned_lyrics,\n",
" clean_text,\n",
" encode_and_align,\n",
")\n",
"from suno_utils.tasks.hoot import (\n",
" _get_alignable_tokens,\n",
" _assign_word_timings,\n",
" _merge_metatags_whitespace,\n",
" _pad_words,\n",
" ctc_align,\n",
" LOGIT_DURATION_S,\n",
" _merge_into_lines,\n",
" \n",
")\n",
"from suno_utils.utils.lyrics import remove_speakers\n",
"from suno_utils.utils.metrics import get_cer\n",
"\n",
"from Bio import Align\n",
"from suno_utils.audio import Audio"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "8be26813",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:51.226595Z",
"start_time": "2024-02-24T14:59:49.104427Z"
}
},
"outputs": [],
"source": [
"model_list = load_model_list(\n",
" # checkpoint_filepath=os.path.join(\"/home/tony/Data/checkpoints/hoot/2023-11-17_15-08-57\", \"28k_ckpt.pt\"),\n",
" checkpoint_filepath=os.path.join(\n",
" \"/home/tony/Data/checkpoints/hoot/2024-01-12_22-51-29\", \"170k_ckpt.pt\"\n",
" ),\n",
" tokenizer_filepath=\"/home/tony/Work/tony/hoot/tokenizers/full/tokenizer_spe_bpe_v20480/tokenizer.model\",\n",
" n_gpus=0,\n",
")\n",
"model = model_list[0][\"model\"]\n",
"tokenizer = model_list[0][\"tokenizer\"]"
]
},
{
"cell_type": "markdown",
"id": "69a9f4ef",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-21T15:20:01.531477Z",
"start_time": "2024-02-21T15:20:01.529735Z"
}
},
"source": [
"# Set the file path"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "faa103f8",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:51.231734Z",
"start_time": "2024-02-24T14:59:51.228890Z"
}
},
"outputs": [],
"source": [
"buggy_url = \"https://app.suno.ai/song/63548e5f-c29b-4bae-930e-490340e19701\""
]
},
{
"cell_type": "markdown",
"id": "96e9bc37",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-21T15:20:03.952638Z",
"start_time": "2024-02-21T15:20:03.950741Z"
}
},
"source": [
"# Try to get the file first"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "fb966d7e",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:51.298358Z",
"start_time": "2024-02-24T14:59:51.233720Z"
}
},
"outputs": [],
"source": [
"buggy_file = os.path.basename(buggy_url)\n",
"if \".mp3\" not in buggy_file:\n",
" buggy_file += \".mp3\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8d26433c",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:52.716278Z",
"start_time": "2024-02-24T14:59:51.300078Z"
}
},
"outputs": [],
"source": [
"buggy_audio = Audio.from_s3(os.path.join(\"s3://suno-data-uploads/studio/uploads/\", buggy_file))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f3957d29",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:53.547131Z",
"start_time": "2024-02-24T14:59:52.718394Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"buggy_audio.play()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "cd4a62be",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:53.551254Z",
"start_time": "2024-02-24T14:59:53.548992Z"
}
},
"outputs": [],
"source": [
"text_prompt = \"\"\"\n",
"君不见黄河之水天上来，奔流到海不复回。\\n君不见高堂明镜悲白发，朝如青丝暮成雪。\\n\\n人生得意须尽欢，莫使金樽空对月。\\n天生我材必有用，千金散尽还复来。\\n烹羊宰牛且为乐，会须一饮三百杯。\\n\\n岑夫子，丹丘生，将进酒，杯莫停。\\n与君歌一曲，请君为我倾耳听。\\n\\n钟鼓馔玉不足贵，但愿长醉不愿醒。\\n古来圣贤皆寂寞，惟有饮者留其名。\\n陈王昔时宴平乐，斗酒十千恣欢谑。\\n\\n主人何为言少钱，径须沽取对君酌。\\n五花马、千金裘，呼儿将出换美酒，与尔同销万古愁。\\n\\n[chorus]\\n钟鼓馔玉不足贵，但愿长醉不愿醒。\\n古来圣贤皆寂寞，惟有饮者留其名。\\n\\n[refrain]\\n五花马、千金裘，呼儿将出换美酒，与尔同销万古愁。\\n\\n{end; vocals:end}\n",
"\"\"\""
]
},
{
"cell_type": "markdown",
"id": "8e6dec9f",
"metadata": {},
"source": [
"# Hoot"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "839bb1cd",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:54.104459Z",
"start_time": "2024-02-24T14:59:53.552566Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WTF \n",
"君不见黄河之水天上来，奔流到海不复回。\n",
"君不见高堂明镜悲白发，朝如青丝暮成雪。\n",
"\n",
"人生得意须尽欢，莫使金樽空对月。\n",
"天生我材必有用，千金散尽还复来。\n",
"烹羊宰牛且为乐，会须一饮三百杯。\n",
"\n",
"岑夫子，丹丘生，将进酒，杯莫停。\n",
"与君歌一曲，请君为我倾耳听。\n",
"\n",
"钟鼓馔玉不足贵，但愿长醉不愿醒。\n",
"古来圣贤皆寂寞，惟有饮者留其名。\n",
"陈王昔时宴平乐，斗酒十千恣欢谑。\n",
"\n",
"主人何为言少钱，径须沽取对君酌。\n",
"五花马、千金裘，呼儿将出换美酒，与尔同销万古愁。\n",
"\n",
"[chorus]\n",
"钟鼓馔玉不足贵，但愿长醉不愿醒。\n",
"古来圣贤皆寂寞，惟有饮者留其名。\n",
"\n",
"[refrain]\n",
"五花马、千金裘，呼儿将出换美酒，与尔同销万古愁。\n",
"\n",
" \n",
"\n",
"WTF 3 ['君不见黄河之水天上来', '奔流到海不复回', '君不见高堂明镜悲白发', '朝如青丝暮成雪', '人生得意须尽欢', '莫使金樽空对月', '天生我材必有用', '千金散尽还复来', '烹羊宰牛且为乐', '会须一饮三百杯', '岑夫子', '丹丘生', '将进酒', '杯莫停', '与君歌一曲', '请君为我倾耳听', '钟鼓馔玉不足贵', '但愿长醉不愿醒', '古来圣贤皆寂寞', '惟有饮者留其名', '陈王昔时宴平乐', '斗酒十千恣欢谑', '主人何为言少钱', '径须沽取对君酌', '五花马', '千金裘', '呼儿将出换美酒', '与尔同销万古愁', '64618757', '钟鼓馔玉不足贵', '但愿长醉不愿醒', '古来圣贤皆寂寞', '惟有饮者留其名', '64158209', '五花马', '千金裘', '呼儿将出换美酒', '与尔同销万古愁']\n",
"WTF 4 ['不天何出水', '天醒来得留到海不不会', '不见高天明子', '悲白发出如成出雪', '人生对一成花我时金成空对月', '天上我不有', '天成三千海呼来', '空人子月', '意散', '成不子', '但上成一我天', '成得一曲天成为我成河天', '如不雪不足会得人成不人', '不来寂我', '如有一有明', '酒我其时欢水天', '不花天天生上花', '酒一同少', '成酒将出花', '美酒一同少歌']\n",
"WTF 4 ['\\n', '君不见黄河之水天上来', '，', '奔流到海不复回', '。\\n', '君不见高堂明镜悲白发', '，', '朝如青丝暮成雪', '。\\n\\n', '人生得意须尽欢', '，', '莫使金樽空对月', '。\\n', '天生我材必有用', '，', '千金散尽还复来', '。\\n', '烹羊宰牛且为乐', '，', '会须一饮三百杯', '。\\n\\n', '岑夫子', '，', '丹丘生', '，', '将进酒', '，', '杯莫停', '。\\n', '与君歌一曲', '，', '请君为我倾耳听', '。\\n\\n', '钟鼓馔玉不足贵', '，', '但愿长醉不愿醒', '。\\n', '古来圣贤皆寂寞', '，', '惟有饮者留其名', '。\\n', '陈王昔时宴平乐', '，', '斗酒十千恣欢谑', '。\\n\\n', '主人何为言少钱', '，', '径须沽取对君酌', '。\\n', '五花马', '、', '千金裘', '，', '呼儿将出换美酒', '，', '与尔同销万古愁', '。\\n\\n', '[chorus]', '\\n', '钟鼓馔玉不足贵', '，', '但愿长醉不愿醒', '。\\n', '古来圣贤皆寂寞', '，', '惟有饮者留其名', '。\\n\\n', '[refrain]', '\\n', '五花马', '、', '千金裘', '，', '呼儿将出换美酒', '，', '与尔同销万古愁', '。\\n\\n \\n']\n",
"WTF 4 []\n"
]
}
],
"source": [
"output_text = encode_and_align(buggy_audio, prior_texts=text_prompt)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "40ace837",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:54.109527Z",
"start_time": "2024-02-24T14:59:54.106726Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"不天何出水 天醒来得留到海不不会 不见高天明子 悲白发出如成出雪 人生对一成花我时金成空对月 天上我不有 天成三千海呼来 空人子月 意散 成不子 但上成一我天 成得一曲天成为我成河天 如不雪不足会得人成不人 不来寂我 如有一有明 酒我其时欢水天 不花天天生上花 酒一同少 成酒将出花 美酒一同少歌\n"
]
}
],
"source": [
"print(output_text)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ec6ac2ab",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:54.727619Z",
"start_time": "2024-02-24T14:59:54.111265Z"
}
},
"outputs": [],
"source": [
"raw_hoot_text = encode(buggy_audio, prior_texts=[text_prompt])"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "3263f883",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T14:59:54.733501Z",
"start_time": "2024-02-24T14:59:54.730310Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"不天生何出水 天醒来得留到海不不会 不见高天明子 悲白发出如成成雪 人生对一成花我时金成空对月 天上我不有 天成三千海呼来 空人子月 意散 成不子 但上成一我天 成得一曲天成为我成河天 如不雪不足会得人成不人 不来寂我 如有一有明 酒我其时欢水天 不花天天生上花 酒一同少 成酒将出花 美酒一同少歌\n"
]
}
],
"source": [
"print(raw_hoot_text)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "b1555071",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T15:00:40.433273Z",
"start_time": "2024-02-24T15:00:40.431174Z"
}
},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "a344ea22",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T15:19:53.545600Z",
"start_time": "2024-02-24T15:19:53.465697Z"
}
},
"outputs": [
{
"ename": "error",
"evalue": "bad escape \\p at position 0",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31merror\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[23], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mre\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfindall\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mp\u001b[39;49m\u001b[38;5;132;43;01m{L}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mraw_hoot_text\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/re.py:240\u001b[0m, in \u001b[0;36mfindall\u001b[0;34m(pattern, string, flags)\u001b[0m\n\u001b[1;32m 232\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfindall\u001b[39m(pattern, string, flags\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m):\n\u001b[1;32m 233\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Return a list of all non-overlapping matches in the string.\u001b[39;00m\n\u001b[1;32m 234\u001b[0m \n\u001b[1;32m 235\u001b[0m \u001b[38;5;124;03m If one or more capturing groups are present in the pattern, return\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 238\u001b[0m \n\u001b[1;32m 239\u001b[0m \u001b[38;5;124;03m Empty matches are included in the result.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 240\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_compile\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpattern\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflags\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mfindall(string)\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/re.py:303\u001b[0m, in \u001b[0;36m_compile\u001b[0;34m(pattern, flags)\u001b[0m\n\u001b[1;32m 301\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m sre_compile\u001b[38;5;241m.\u001b[39misstring(pattern):\n\u001b[1;32m 302\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfirst argument must be string or compiled pattern\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 303\u001b[0m p \u001b[38;5;241m=\u001b[39m \u001b[43msre_compile\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompile\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpattern\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflags\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 304\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (flags \u001b[38;5;241m&\u001b[39m DEBUG):\n\u001b[1;32m 305\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(_cache) \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m _MAXCACHE:\n\u001b[1;32m 306\u001b[0m \u001b[38;5;66;03m# Drop the oldest item\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/sre_compile.py:788\u001b[0m, in \u001b[0;36mcompile\u001b[0;34m(p, flags)\u001b[0m\n\u001b[1;32m 786\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m isstring(p):\n\u001b[1;32m 787\u001b[0m pattern \u001b[38;5;241m=\u001b[39m p\n\u001b[0;32m--> 788\u001b[0m p \u001b[38;5;241m=\u001b[39m \u001b[43msre_parse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflags\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 789\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 790\u001b[0m pattern \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/sre_parse.py:955\u001b[0m, in \u001b[0;36mparse\u001b[0;34m(str, flags, state)\u001b[0m\n\u001b[1;32m 952\u001b[0m state\u001b[38;5;241m.\u001b[39mstr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m\n\u001b[1;32m 954\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 955\u001b[0m p \u001b[38;5;241m=\u001b[39m \u001b[43m_parse_sub\u001b[49m\u001b[43m(\u001b[49m\u001b[43msource\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflags\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m&\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mSRE_FLAG_VERBOSE\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 956\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m Verbose:\n\u001b[1;32m 957\u001b[0m \u001b[38;5;66;03m# the VERBOSE flag was switched on inside the pattern. to be\u001b[39;00m\n\u001b[1;32m 958\u001b[0m \u001b[38;5;66;03m# on the safe side, we'll parse the whole thing again...\u001b[39;00m\n\u001b[1;32m 959\u001b[0m state \u001b[38;5;241m=\u001b[39m State()\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/sre_parse.py:444\u001b[0m, in \u001b[0;36m_parse_sub\u001b[0;34m(source, state, verbose, nested)\u001b[0m\n\u001b[1;32m 442\u001b[0m start \u001b[38;5;241m=\u001b[39m source\u001b[38;5;241m.\u001b[39mtell()\n\u001b[1;32m 443\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 444\u001b[0m itemsappend(\u001b[43m_parse\u001b[49m\u001b[43m(\u001b[49m\u001b[43msource\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnested\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 445\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mnested\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mand\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mitems\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 446\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m sourcematch(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m|\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 447\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/sre_parse.py:526\u001b[0m, in \u001b[0;36m_parse\u001b[0;34m(source, state, verbose, nested, first)\u001b[0m\n\u001b[1;32m 523\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m\n\u001b[1;32m 525\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m this[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m--> 526\u001b[0m code \u001b[38;5;241m=\u001b[39m \u001b[43m_escape\u001b[49m\u001b[43m(\u001b[49m\u001b[43msource\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mthis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 527\u001b[0m subpatternappend(code)\n\u001b[1;32m 529\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m this \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m SPECIAL_CHARS:\n",
"File \u001b[0;32m~/anaconda3/envs/suno_env/lib/python3.10/sre_parse.py:427\u001b[0m, in \u001b[0;36m_escape\u001b[0;34m(source, escape, state)\u001b[0m\n\u001b[1;32m 425\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(escape) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m 426\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m c \u001b[38;5;129;01min\u001b[39;00m ASCIILETTERS:\n\u001b[0;32m--> 427\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m source\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbad escape \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m escape, \u001b[38;5;28mlen\u001b[39m(escape))\n\u001b[1;32m 428\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m LITERAL, \u001b[38;5;28mord\u001b[39m(escape[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 429\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m:\n",
"\u001b[0;31merror\u001b[0m: bad escape \\p at position 0"
]
}
],
"source": [
"re.findall(r\"\\p{L}\", raw_hoot_text)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "d81c2a26",
"metadata": {
"ExecuteTime": {
"end_time": "2024-02-24T15:25:22.116210Z",
"start_time": "2024-02-24T15:25:22.112675Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"['',\n",
" '不天生何出水',\n",
" ' ',\n",
" '天醒来得留到海不不会',\n",
" ' ',\n",
" '不见高天明子',\n",
" ' ',\n",
" '悲白发出如成成雪',\n",
" ' ',\n",
" '人生对一成花我时金成空对月',\n",
" ' ',\n",
" '天上我不有',\n",
" ' ',\n",
" '天成三千海呼来',\n",
" ' ',\n",
" '空人子月',\n",
" ' ',\n",
" '意散',\n",
" ' ',\n",
" '成不子',\n",
" ' ',\n",
" '但上成一我天',\n",
" ' ',\n",
" '成得一曲天成为我成河天',\n",
" ' ',\n",
" '如不雪不足会得人成不人',\n",
" ' ',\n",
" '不来寂我',\n",
" ' ',\n",
" '如有一有明',\n",
" ' ',\n",
" '酒我其时欢水天',\n",
" ' ',\n",
" '不花天天生上花',\n",
" ' ',\n",
" '酒一同少',\n",
" ' ',\n",
" '成酒将出花',\n",
" ' ',\n",
" '美酒一同少歌',\n",
" '']"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"re.split(\"([\\w'\\-]+)\", raw_hoot_text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c74c7e17",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "suno_env",
"language": "python",
"name": "suno_env"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
},
"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
}