{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "c666bc86", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:43.754629Z", "start_time": "2024-01-20T18:32:43.634685Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "a10-yul-dev-node-444\r\n" ] } ], "source": [ "!echo $HOSTNAME" ] }, { "cell_type": "code", "execution_count": 2, "id": "08218f19", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:43.757727Z", "start_time": "2024-01-20T18:32:43.755992Z" } }, "outputs": [], "source": [ "import os\n", "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\"" ] }, { "cell_type": "code", "execution_count": 3, "id": "76fc0b2c", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:43.814199Z", "start_time": "2024-01-20T18:32:43.759128Z" } }, "outputs": [], "source": [ "# vocab: \n", "# 0-60_000 text\n", "# 1x0-3999 semantic\n", "# 8x0-4095 coarse\n", "\n", "# 4000 semantic pad token\n", "# 4001 semantic infer token\n", "# 2048 coarse pad token\n", "# 2049 coarse infer token\n", "\n", "# Memmaps:\n", "# Nx9x3584 for audio tokens\n", "# Jsons:\n", "# N*Dict with meta keys \n", "# \"dataset\"\n", "# \"original_id\", \"original_duration_s\",\n", "# \"start_s\", \"end_s\", \n", "# \"text_segments\", \"private_text_segments\",\n", "# \"text\", \"private_text\",\n", "# \"tags\", \"private_tags\",\n", "# \"views\",\n", "# Dict with meta keys {\"dataset\": [\"idx_list\"]}\n", "\n", "# Bundles (mert_v2_2x1k & dac_2c_25_8):\n", "# s3://suno-data/datasets/bundles/\n", "# v1/youtube_music\n", "# v1/genius_hq\n", "# v1/jamendo\n", "# v1/imslp\n", "# v2/pond5\n", "# v2/deezer\n", "# v2/ytm_tagged\n", "# v2/ytm_mb" ] }, { "cell_type": "code", "execution_count": 4, "id": "ce43e8ad", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:44.330605Z", "start_time": "2024-01-20T18:32:43.815683Z" } }, "outputs": [], "source": [ "from matplotlib import pyplot as plt\n", "\n", "import sys\n", "\n", "sys.path.insert(0, \"/home/tony/Work/glockenspiel/sunoGPT/scripts/\")\n", "\n", "from data_preparation_7b import *" ] }, { "cell_type": "code", "execution_count": 5, "id": "17f66742", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:44.333630Z", "start_time": "2024-01-20T18:32:44.331835Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "4000 2048\n" ] } ], "source": [ "print(SEMANTIC_CODEBOOK_SIZE, COARSE_CODEBOOK_SIZE)" ] }, { "cell_type": "code", "execution_count": 6, "id": "d188ba34", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:44.390272Z", "start_time": "2024-01-20T18:32:44.334619Z" } }, "outputs": [], "source": [ "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/genius_hq.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/youtube_music.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/jamendo.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/imslp.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/pond5_music.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/deezer.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/ytm_tagged.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/musescore.jsonl /app/suno/data/chirp_v3/metadata/\n", "# !aws s3 cp s3://suno-data/georg/data/chirp_v2_5/filtered_metas/ytm_mb.jsonl /app/suno/data/chirp_v3/metadata/" ] }, { "cell_type": "code", "execution_count": 7, "id": "40767a44", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:32:44.447945Z", "start_time": "2024-01-20T18:32:44.391682Z" } }, "outputs": [], "source": [ "OUT_DATA_DIR = \"/app/suno/data/chirp_v3_ft_v3\"\n", "os.makedirs(OUT_DATA_DIR, exist_ok=True)\n", "METAS_DIR = \"/home/tony/Work/tony/FineTuning_chirp_v3/metadata/\"\n", "NJOBS = 60\n", "CHUNKSIZE = 60" ] }, { "cell_type": "code", "execution_count": 8, "id": "b30bfb77", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:34:50.653465Z", "start_time": "2024-01-20T18:32:44.449522Z" } }, "outputs": [], "source": [ "# load manifests of IDs and text and tags etc\n", "meta_info_map = {\n", " \"genius_hq\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"genius_hq_v3.jsonl\"))},\n", "# \"youtube_music\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"youtube_music.jsonl\"))},\n", "# \"jamendo\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"jamendo.jsonl\"))},\n", "# \"imslp\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"imslp.jsonl\"))},\n", " \"pond5_music\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"pond5_music_v1.jsonl\"))},\n", "# \"deezer\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"deezer.jsonl\"))},\n", "# \"ytm_tagged\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"ytm_tagged.jsonl\"))},\n", "# \"musescore\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"musescore.jsonl\"))},\n", " # \"ytm_mb\": {m[\"id\"]: m for m in read_jsonl(os.path.join(METAS_DIR, \"ytm_mb.jsonl\"))},\n", "}" ] }, { "cell_type": "code", "execution_count": 9, "id": "4a145268", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:34:52.469698Z", "start_time": "2024-01-20T18:34:50.655901Z" } }, "outputs": [], "source": [ "with open(\"/app/suno/data/preprocessing/meta_cutoff_freq.json\", \"r\") as fp:\n", " meta_cutoff_freq = json.load(fp)" ] }, { "cell_type": "code", "execution_count": 10, "id": "2a01e35c", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:35:16.533701Z", "start_time": "2024-01-20T18:34:52.471396Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "start prepare data\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:12<00:00, 12.43s/it]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "7 hours of genius_hq_lyrics_foreign\n", "10 hours of genius_hq_lyrics\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:11<00:00, 11.43s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2 hours of pond5_music\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "# (start_idx, end_idx), n_archives_semantic, n_archives_coarse\n", "datasets = [\n", " # (\"youtube_music\", \"v1\", (0, 1), 1, 1),\n", " (\"genius_hq\", \"v1\", (0, 1), 1, 1),\n", " # (\"imslp\", \"v1\", (0, 1), 1, 1),\n", " # (\"jamendo\", \"v1\", (0, 1), 1, 1),\n", " (\"pond5_music\", \"v2\", (0, 1), 1, 1),\n", " # (\"deezer\", \"v2\", (0, 1), 1, 1),\n", " # (\"ytm_tagged\", \"v2\", (0, 1), 1, 1),\n", " # (\"musescore\", \"v2\", (0, 1), 1, 1),\n", " # (\"ytm_mb\", \"v2\", (0, 1), 1, 1),\n", "]\n", "prep_data(\n", " datasets,\n", " out_data_dir=OUT_DATA_DIR,\n", " meta_info_map=meta_info_map,\n", " meta_cutoff_freq=meta_cutoff_freq, # TODO: This arg should be removed in the longer run...\n", " is_val=True,\n", " njobs=NJOBS,\n", " chunksize=CHUNKSIZE,\n", ")\n", "# 24 hours of youtube_music\n", "# 3 hours of youtube_music_lyrics\n", "# 2 hours of youtube_music_lyrics_foreign\n", "# 4 hours of genius_hq\n", "# 9 hours of genius_hq_lyrics\n", "# 5 hours of genius_hq_lyrics_foreign\n", "# 17 hours of imslp\n", "# 30 hours of jamendo\n", "# 14 hours of pond5_music\n", "# 12 hours of deezer\n", "# 7 hours of deezer_lyrics\n", "# 8 hours of deezer_lyrics_foreign\n", "# 30 hours of ytm_tagged\n", "# 3 hours of musescore_lyrics\n", "# 30 hours of ytm_mb" ] }, { "cell_type": "code", "execution_count": 11, "id": "956bd1f3", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T18:35:16.536356Z", "start_time": "2024-01-20T18:35:16.534932Z" } }, "outputs": [], "source": [ "# Stats:\n", "# tot expected: 4.5Tb\n", "# speed for ytm_mb: 53129/200*(3*60+40)/60/60 == 16 hours" ] }, { "cell_type": "code", "execution_count": 12, "id": "a2dfa127", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.381518Z", "start_time": "2024-01-20T18:35:16.537322Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "start prepare data\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 72/72 [54:36<00:00, 45.51s/it]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "43,921 hours of genius_hq_lyrics\n", "23,734 hours of genius_hq_lyrics_foreign\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 69/69 [23:41<00:00, 20.60s/it]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8,701 hours of pond5_music\n" ] } ], "source": [ "# (start_idx, end_idx), n_archives_semantic, n_archives_coarse\n", "datasets = [\n", " # (\"youtube_music\", \"v1\", (1, 4204), 1, 1),\n", " (\"genius_hq\", \"v1\", (1, 4302), 1, 1),\n", " # (\"imslp\", \"v1\", (1, 558), 1, 1),\n", " # (\"jamendo\", \"v1\", (1, 112), 1, 1),\n", " (\"pond5_music\", \"v2\", (1, 4138), 1, 1),\n", " # (\"deezer\", \"v2\", (1, 1538), 1, 1),\n", " # (\"ytm_tagged\", \"v2\", (1, 5545), 1, 1),\n", " # (\"musescore\", \"v2\", (1, 33), 1, 1),\n", "# (\"ytm_mb\", \"v2\", (1, 53129), 1, 1),\n", "# (\"ytm_mb\", \"v2\", (1, 50001), 1, 1),\n", "]\n", "prep_data(\n", " datasets,\n", " out_data_dir=OUT_DATA_DIR,\n", " meta_info_map=meta_info_map,\n", " meta_cutoff_freq=meta_cutoff_freq, # TODO: This arg should be removed in the longer run...\n", " is_val=False,\n", " njobs=NJOBS,\n", " chunksize=CHUNKSIZE,\n", ")\n", "# youtube_music: ~1h runtime\n", "# 105,498 hours of youtube_music\n", "# 12,168 hours of youtube_music_lyrics\n", "# 10,363 hours of youtube_music_lyrics_foreign\n", "# genius_hq: ~1h runtime\n", "# 17,784 hours of genius_hq\n", "# 41,544 hours of genius_hq_lyrics\n", "# 17,469 hours of genius_hq_lyrics_foreign\n", "# imslp: ~8m runtime\n", "# 12,175 hours of imslp\n", "# jamendo: ~27m runtime\n", "# 3,251 hours of jamendo\n", "# pond5_music: ~51m runtime\n", "# 58,592 hours of pond5_music\n", "# deezer: ~19m runtime\n", "# 12,181 hours of deezer\n", "# 10,132 hours of deezer_lyrics\n", "# 6,770 hours of deezer_lyrics_foreign\n", "# ytm_tagged: ~1h runtime\n", "# 141,476 hours of ytm_tagged\n", "# musescore: ~5m runtime\n", "# 103 hours of ytm_tagged\n", "# ytm_mb: ~12h runtime\n", "# 1,642,164 hours of ytm_mb" ] }, { "cell_type": "code", "execution_count": 13, "id": "d169a93b", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.847855Z", "start_time": "2024-01-20T19:58:58.383386Z" } }, "outputs": [ { "ename": "NameError", "evalue": "name 'BREAK' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[13], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mBREAK\u001b[49m\n", "\u001b[0;31mNameError\u001b[0m: name 'BREAK' is not defined" ] } ], "source": [ "BREAK" ] }, { "cell_type": "code", "execution_count": null, "id": "efcc774c", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.849179Z", "start_time": "2024-01-20T19:58:58.849170Z" } }, "outputs": [], "source": [ "# freq info" ] }, { "cell_type": "code", "execution_count": null, "id": "d1c95d44", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.850027Z", "start_time": "2024-01-20T19:58:58.850018Z" } }, "outputs": [], "source": [ "# with open(\"/app/suno/data/preprocessing/meta_cutoff_freq.json\", \"r\") as fp:\n", "# meta_cutoff_freq = json.load(fp)" ] }, { "cell_type": "code", "execution_count": null, "id": "2ab57df8", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.850886Z", "start_time": "2024-01-20T19:58:58.850878Z" } }, "outputs": [], "source": [ "# verify\n", "mm = np.memmap(os.path.join(OUT_DATA_DIR, \"data_val.bin\"), dtype=np.uint16, mode=\"r\")\n", "metas = read_jsonl(os.path.join(OUT_DATA_DIR,\"metas_val.jsonl\"))\n", "mm = mm.reshape(-1, 3008, 13)\n", "assert(len(mm) == len(metas))\n", "assert(mm[:100,:,0].min() >= 0)\n", "assert(mm[:100,:,0].max() <= 4000)\n", "assert(mm[:100,:,1:].min() >= 0)\n", "assert(mm[:100,:,1:].max() <= 4096)" ] }, { "cell_type": "code", "execution_count": null, "id": "cfaf6050", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.851438Z", "start_time": "2024-01-20T19:58:58.851430Z" } }, "outputs": [], "source": [ "metas[797]" ] }, { "cell_type": "code", "execution_count": null, "id": "9cd8eb63", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.852219Z", "start_time": "2024-01-20T19:58:58.852211Z" } }, "outputs": [], "source": [ "# # verify\n", "# mm = np.memmap(os.path.join(OUT_DATA_DIR, \"data_tr.bin\"), dtype=np.uint16, mode=\"r\")\n", "# metas = read_jsonl(os.path.join(OUT_DATA_DIR,\"metas_tr.jsonl\"))\n", "# mm = mm.reshape(-1, 3008, 13)\n", "# assert(len(mm) == len(metas))\n", "# assert(mm[:100,:,0].min() >= 0)\n", "# assert(mm[:100,:,0].max() <= 4000)\n", "# assert(mm[:100,:,1:].min() >= 0)\n", "# assert(mm[:100,:,1:].max() <= 4096)" ] }, { "cell_type": "code", "execution_count": null, "id": "814a34af", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.852936Z", "start_time": "2024-01-20T19:58:58.852928Z" } }, "outputs": [], "source": [ "# for meta in metas:\n", "# if meta[\"id\"] in meta_cutoff_freq:\n", "# meta[\"cutoff_freq\"] = meta_cutoff_freq[meta[\"id\"]]\n", "\n", "# write_jsonl(metas, os.path.join(OUT_DATA_DIR,\"metas_tr.jsonl\"))" ] }, { "cell_type": "code", "execution_count": null, "id": "f5bdf8ac", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.853955Z", "start_time": "2024-01-20T19:58:58.853943Z" } }, "outputs": [], "source": [ "# !du -hs /mnt/data/georg/data/chirp_v2/data_tr.bin\n", "# # 1003G" ] }, { "cell_type": "code", "execution_count": null, "id": "cbcbca32", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.855349Z", "start_time": "2024-01-20T19:58:58.855341Z" } }, "outputs": [], "source": [ "# randomly listen to some stuff\n", "from suno_utils.tasks.dac_2c_12cb import preload_models as preload_codec_models\n", "from suno_utils.tasks.dac_2c_12cb import (\n", " encode as codec_encode,\n", " decode as codec_decode,\n", " EMBEDDING_RATE as CODEC_EMBEDDING_RATE,\n", ")\n", "\n", "_ = preload_codec_models(\"/app/suno/tony/v3/dac_2c_25x12.pt\")\n", "mm = np.memmap(os.path.join(OUT_DATA_DIR, \"data_val.bin\"), dtype=np.uint16, mode=\"r\")\n", "mm = mm.reshape(-1, 3008, 13)\n", "test_metas = read_jsonl(os.path.join(OUT_DATA_DIR, \"metas_val.jsonl\"))\n", "test_info = read_json(os.path.join(OUT_DATA_DIR, \"info_val.json\"))\n", "assert len(test_metas) == len(mm)\n", "idx_list = list(range(len(test_metas)))\n", "# random.shuffle(idx_list)\n", "# idx_list = [idx for idx in idx_list if \"text\" in test_metas[idx]]\n", "print(len(mm))" ] }, { "cell_type": "code", "execution_count": null, "id": "7008ddc7", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.856171Z", "start_time": "2024-01-20T19:58:58.856162Z" } }, "outputs": [], "source": [ "# show text and audio\n", "# idx = random.choice(idx_list)\n", "# idx = random.choice(test_info[\"pond5_music\"][\"idx_list\"])\n", "idx = random.choice(test_info[\"genius_hq_lyrics\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"musescore_lyrics\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"deezer_lyrics\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"youtube_music_lyrics_foreign\"][\"idx_list\"])\n", "# idx_key = random.choice(list(test_info.keys()))\n", "# print(idx_key)\n", "# idx = random.choice(test_info[idx_key][\"idx_list\"])\n", "assert \"original_duration_s\" in test_metas[idx]\n", "print(\"tags:\", test_metas[idx].get(\"tags\"))\n", "arr = mm[idx, 1:].copy().astype(np.int16)[:, 1:]\n", "pad_idx_arr = np.where(arr == 4096)[0]\n", "if len(pad_idx_arr) > 0:\n", " arr = arr[: pad_idx_arr[0], :]\n", "a = codec_decode(arr)\n", "a.play(compress=False)\n", "print(\"text:\", test_metas[idx].get(\"text\"))\n", "plt.plot(a.array_float[0])" ] }, { "cell_type": "code", "execution_count": null, "id": "f818ab33", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.856882Z", "start_time": "2024-01-20T19:58:58.856874Z" } }, "outputs": [], "source": [ "test_metas[idx]" ] }, { "cell_type": "code", "execution_count": null, "id": "87b856f6", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "62fb16fc", "metadata": {}, "source": [ "### try same with train" ] }, { "cell_type": "code", "execution_count": null, "id": "f987040e", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.857807Z", "start_time": "2024-01-20T19:58:58.857800Z" } }, "outputs": [], "source": [ "%matplotlib inline\n", "from matplotlib import pyplot as plt" ] }, { "cell_type": "code", "execution_count": null, "id": "4471a7fb", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.858733Z", "start_time": "2024-01-20T19:58:58.858724Z" } }, "outputs": [], "source": [ "# randomly listen to some stuff\n", "from suno_utils.tasks.dac_2c_12cb import preload_models as preload_codec_models\n", "from suno_utils.tasks.dac_2c_12cb import (\n", " encode as codec_encode,\n", " decode as codec_decode, \n", " EMBEDDING_RATE as CODEC_EMBEDDING_RATE,\n", ")\n", "from suno_utils.utils.text import read_jsonl, read_json\n", "_ = preload_codec_models(\"/app/suno/models/dac_2c_25x12.pt\")\n", "mm = np.memmap(\"/mnt/localdisk/data/data_tr.bin\", dtype=np.uint16, mode=\"r\")\n", "mm = mm.reshape(-1, 3008, 13)\n", "test_metas = read_jsonl(\"/mnt/localdisk/data/metas_tr.jsonl\")\n", "test_info = read_json(\"/mnt/localdisk/data/info_tr.json\")\n", "assert(len(test_metas) == len(mm))\n", "idx_list = list(range(len(test_metas)))\n", "#random.shuffle(idx_list)\n", "#idx_list = [idx for idx in idx_list if \"text\" in test_metas[idx]]\n", "print(len(mm))" ] }, { "cell_type": "code", "execution_count": null, "id": "ecb73f42", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.859387Z", "start_time": "2024-01-20T19:58:58.859380Z" } }, "outputs": [], "source": [ "import random\n", "# show text and audio\n", "# idx = random.choice(idx_list)\n", "# idx = random.choice(test_info[\"pond5_music\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"genius_hq_lyrics\"][\"idx_list\"])\n", "idx = random.choice(test_info[\"ytm_mb\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"musescore_lyrics\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"deezer_lyrics\"][\"idx_list\"])\n", "# idx = random.choice(test_info[\"youtube_music_lyrics_foreign\"][\"idx_list\"])\n", "# idx_key = random.choice(list(test_info.keys()))\n", "# print(idx_key)\n", "# idx = random.choice(test_info[idx_key][\"idx_list\"])\n", "assert(\"original_duration_s\" in test_metas[idx])\n", "print(\"tags:\", test_metas[idx].get(\"tags\"))\n", "arr = mm[idx,1:].copy().astype(np.int16)[:,1:]\n", "pad_idx_arr = np.where(arr == 4096)[0]\n", "if len(pad_idx_arr) > 0:\n", " arr = arr[:pad_idx_arr[0],:]\n", "a = codec_decode(arr)\n", "a.play(compress=False)\n", "print(\"text:\", test_metas[idx].get(\"text\"))\n", "plt.plot(a.array_float[0])" ] }, { "cell_type": "code", "execution_count": null, "id": "ee88a2eb", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "1d977073", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "c2653b41", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "067a561b", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "73c92bda", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "08665ec0", "metadata": {}, "source": [ "## Playground" ] }, { "cell_type": "markdown", "id": "747f0363", "metadata": {}, "source": [ "#### get all tags" ] }, { "cell_type": "code", "execution_count": null, "id": "73286512", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.859964Z", "start_time": "2024-01-20T19:58:58.859956Z" } }, "outputs": [], "source": [ "test_metas = read_jsonl(\"/mnt/data/georg/data/chirp_v2/metas_val.jsonl\")" ] }, { "cell_type": "code", "execution_count": null, "id": "a3ed7922", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.861012Z", "start_time": "2024-01-20T19:58:58.861004Z" } }, "outputs": [], "source": [ "tags = []\n", "for e in train_metas:\n", " tags.extend(e.get(\"tags\", []))" ] }, { "cell_type": "code", "execution_count": null, "id": "2eed69a8", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.862072Z", "start_time": "2024-01-20T19:58:58.862065Z" } }, "outputs": [], "source": [ "vc_tags = pd.Series(tags).value_counts()" ] }, { "cell_type": "code", "execution_count": null, "id": "bf1c83e8", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.862932Z", "start_time": "2024-01-20T19:58:58.862924Z" } }, "outputs": [], "source": [ "vc_tags.head(5)" ] }, { "cell_type": "code", "execution_count": null, "id": "f76f1e83", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.863509Z", "start_time": "2024-01-20T19:58:58.863502Z" } }, "outputs": [], "source": [ "vc_tags = vc_tags.to_frame()" ] }, { "cell_type": "code", "execution_count": null, "id": "6766efb1", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.864298Z", "start_time": "2024-01-20T19:58:58.864290Z" } }, "outputs": [], "source": [ "vc_tags.tail()" ] }, { "cell_type": "code", "execution_count": null, "id": "fece8109", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.865008Z", "start_time": "2024-01-20T19:58:58.865000Z" } }, "outputs": [], "source": [ "a = vc_tags[vc_tags[\"count\"]>=3][\"count\"].to_dict()" ] }, { "cell_type": "code", "execution_count": null, "id": "52e1a982", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.865685Z", "start_time": "2024-01-20T19:58:58.865677Z" } }, "outputs": [], "source": [ "test_metas = read_jsonl(\"/mnt/data/georg/data/chirp_v2/metas_val.jsonl\")\n", "test_info = read_json(\"/mnt/data/georg/data/chirp_v2/info_val.json\")" ] }, { "cell_type": "code", "execution_count": null, "id": "b6b9f19e", "metadata": { "ExecuteTime": { "end_time": "2024-01-20T19:58:58.866479Z", "start_time": "2024-01-20T19:58:58.866471Z" } }, "outputs": [], "source": [ "idx = random.choice(test_info[\"musescore_lyrics\"][\"idx_list\"])\n", "print(idx)\n", "m = test_metas[idx]\n", "re.sub(r\"\\[.*?\\]\", \"\", m[\"text\"])" ] }, { "cell_type": "code", "execution_count": null, "id": "5dffab2d", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "4531aac2", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "f0e1aafb", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "143ac0a7", "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": "3.10.13" }, "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 }