|
3185 | 3185 | "drive.mount('/content/drive')"
|
3186 | 3186 | ],
|
3187 | 3187 | "metadata": {
|
3188 |
| - "id": "UTPBozTaQ6ku", |
3189 |
| - "outputId": "163adf96-31ef-44c0-c999-ce22159c225c", |
3190 | 3188 | "colab": {
|
3191 | 3189 | "base_uri": "https://localhost:8080/"
|
3192 |
| - } |
| 3190 | + }, |
| 3191 | + "id": "UTPBozTaQ6ku", |
| 3192 | + "outputId": "163adf96-31ef-44c0-c999-ce22159c225c" |
3193 | 3193 | },
|
3194 | 3194 | "execution_count": 11,
|
3195 | 3195 | "outputs": [
|
|
3219 | 3219 | ],
|
3220 | 3220 | "cell_type": "code",
|
3221 | 3221 | "metadata": {
|
3222 |
| - "id": "d8CFqE0zRGdr", |
3223 |
| - "outputId": "ef54f2ff-2700-4f32-a444-42849b940811", |
3224 | 3222 | "colab": {
|
3225 | 3223 | "base_uri": "https://localhost:8080/"
|
3226 |
| - } |
| 3224 | + }, |
| 3225 | + "id": "d8CFqE0zRGdr", |
| 3226 | + "outputId": "ef54f2ff-2700-4f32-a444-42849b940811" |
3227 | 3227 | },
|
3228 | 3228 | "execution_count": 14,
|
3229 | 3229 | "outputs": [
|
|
5051 | 5051 | "100% 15/15 [00:18<00:00, 1.24s/it]\n",
|
5052 | 5052 | "100% 15/15 [00:19<00:00, 1.28s/it]\n",
|
5053 | 5053 | "100% 15/15 [00:17<00:00, 1.13s/it]\n",
|
5054 |
| - " 53% 8/15 [00:11<00:06, 1.04it/s]" |
| 5054 | + "100% 15/15 [00:17<00:00, 1.14s/it]\n", |
| 5055 | + "training done\n", |
| 5056 | + "[rank0]:[W427 14:20:02.508797621 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())\n", |
| 5057 | + "\"/usr/local/envs/GPTSoVITS/bin/python\" GPT_SoVITS/s1_train.py --config_file \"/content/GPT-SoVITS/TEMP/tmp_s1.yaml\" \n", |
| 5058 | + "Seed set to 1234\n", |
| 5059 | + "Using 16bit Automatic Mixed Precision (AMP)\n", |
| 5060 | + "GPU available: True (cuda), used: True\n", |
| 5061 | + "TPU available: False, using: 0 TPU cores\n", |
| 5062 | + "HPU available: False, using: 0 HPUs\n", |
| 5063 | + "/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_lightning_module.py:29: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n", |
| 5064 | + "<All keys matched successfully>\n", |
| 5065 | + "ckpt_path: None\n", |
| 5066 | + "Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1\n", |
| 5067 | + "----------------------------------------------------------------------------------------------------\n", |
| 5068 | + "distributed_backend=nccl\n", |
| 5069 | + "All distributed processes registered. Starting with 1 processes\n", |
| 5070 | + "----------------------------------------------------------------------------------------------------\n", |
| 5071 | + "\n", |
| 5072 | + "semantic_data_len: 17\n", |
| 5073 | + "phoneme_data_len: 17\n", |
| 5074 | + " item_name semantic_audio\n", |
| 5075 | + "0 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00008... 520 271 105 280 280 280 280 280 280 105 72 570...\n", |
| 5076 | + "1 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00016... 54 65 910 509 902 278 668 270 270 668 668 942 ...\n", |
| 5077 | + "2 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00023... 520 53 574 96 773 479 295 479 683 814 96 96 35...\n", |
| 5078 | + "3 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00035... 1012 574 28 290 13 32 214 953 5 239 773 773 92...\n", |
| 5079 | + "4 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00048... 54 365 382 272 132 902 52 45 298 487 668 27 81...\n", |
| 5080 | + "5 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00053... 520 53 53 875 54 490 524 53 234 1012 756 445 9...\n", |
| 5081 | + "6 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00065... 520 398 35 130 931 148 1023 630 232 574 244 10...\n", |
| 5082 | + "7 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00071... 520 53 53 760 601 549 225 666 845 963 705 603 ...\n", |
| 5083 | + "8 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00085... 486 937 574 96 921 921 683 132 921 539 32 545 ...\n", |
| 5084 | + "9 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00014... 520 53 405 721 214 505 991 327 145 597 668 161...\n", |
| 5085 | + "10 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00019... 1005 804 837 366 771 850 850 945 850 850 850 2...\n", |
| 5086 | + "11 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00028... 520 105 280 280 875 271 280 53 234 885 566 756...\n", |
| 5087 | + "12 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00046... 520 271 105 105 105 105 105 105 105 105 72 29 ...\n", |
| 5088 | + "13 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00051... 913 699 592 575 641 810 122 106 661 979 979 53...\n", |
| 5089 | + "14 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00055... 214 190 500 108 958 556 395 790 268 796 528 44...\n", |
| 5090 | + "15 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00067... 520 540 59 748 748 509 509 539 171 566 96 814 ...\n", |
| 5091 | + "16 vocal_春日影TFT.mp3.reformatted.wav_10.flac_00077... 520 280 486 486 486 486 486 486 280 53 773 783...\n", |
| 5092 | + "Traceback (most recent call last):\n", |
| 5093 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py\", line 152, in init_batch\n", |
| 5094 | + " phoneme_ids = cleaned_text_to_sequence(phoneme, version)\n", |
| 5095 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/text/__init__.py\", line 26, in cleaned_text_to_sequence\n", |
| 5096 | + " phones = [_symbol_to_id_v2[symbol] for symbol in cleaned_text]\n", |
| 5097 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/text/__init__.py\", line 26, in <listcomp>\n", |
| 5098 | + " phones = [_symbol_to_id_v2[symbol] for symbol in cleaned_text]\n", |
| 5099 | + "KeyError: ''\n", |
| 5100 | + "Traceback (most recent call last):\n", |
| 5101 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py\", line 152, in init_batch\n", |
| 5102 | + " phoneme_ids = cleaned_text_to_sequence(phoneme, version)\n", |
| 5103 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/text/__init__.py\", line 26, in cleaned_text_to_sequence\n", |
| 5104 | + " phones = [_symbol_to_id_v2[symbol] for symbol in cleaned_text]\n", |
| 5105 | + " File \"/content/GPT-SoVITS/GPT_SoVITS/text/__init__.py\", line 26, in <listcomp>\n", |
| 5106 | + " phones = [_symbol_to_id_v2[symbol] for symbol in cleaned_text]\n", |
| 5107 | + "KeyError: ''\n", |
| 5108 | + "there are 2 semantic datas not in phoneme datas\n", |
| 5109 | + "deleted 4 audios who's phoneme/sec are bigger than 25 or smaller than 3\n", |
| 5110 | + "dataset.__len__(): 99\n", |
| 5111 | + "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n", |
| 5112 | + "\n", |
| 5113 | + " | Name | Type | Params | Mode \n", |
| 5114 | + "-------------------------------------------------------\n", |
| 5115 | + "0 | model | Text2SemanticDecoder | 77.6 M | train\n", |
| 5116 | + "-------------------------------------------------------\n", |
| 5117 | + "77.6 M Trainable params\n", |
| 5118 | + "0 Non-trainable params\n", |
| 5119 | + "77.6 M Total params\n", |
| 5120 | + "310.426 Total estimated model params size (MB)\n", |
| 5121 | + "257 Modules in train mode\n", |
| 5122 | + "0 Modules in eval mode\n", |
| 5123 | + "/usr/local/envs/GPTSoVITS/lib/python3.10/site-packages/torch/utils/data/dataloader.py:617: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n", |
| 5124 | + " warnings.warn(\n", |
| 5125 | + "/usr/local/envs/GPTSoVITS/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py:310: The number of training batches (15) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.\n", |
| 5126 | + "Epoch 14: 100% 15/15 [00:05<00:00, 2.93it/s, v_num=0, total_loss_step=829.0, lr_step=0.002, top_3_acc_step=0.669, total_loss_epoch=4.8e+3, lr_epoch=0.002, top_3_acc_epoch=0.737] `Trainer.fit` stopped: `max_epochs=15` reached.\n", |
| 5127 | + "Epoch 14: 100% 15/15 [00:11<00:00, 1.31it/s, v_num=0, total_loss_step=829.0, lr_step=0.002, top_3_acc_step=0.669, total_loss_epoch=4.8e+3, lr_epoch=0.002, top_3_acc_epoch=0.737]\n" |
5055 | 5128 | ]
|
5056 | 5129 | }
|
5057 | 5130 | ],
|
|
5080 | 5153 | ],
|
5081 | 5154 | "metadata": {
|
5082 | 5155 | "id": "kWSUFLBmLQK4",
|
5083 |
| - "outputId": "46f257f4-e460-4363-b707-026c6e8e48b1", |
5084 | 5156 | "colab": {
|
5085 | 5157 | "base_uri": "https://localhost:8080/"
|
5086 |
| - } |
| 5158 | + }, |
| 5159 | + "outputId": "46f257f4-e460-4363-b707-026c6e8e48b1" |
5087 | 5160 | },
|
5088 | 5161 | "execution_count": 8,
|
5089 | 5162 | "outputs": [
|
|
5128 | 5201 | ],
|
5129 | 5202 | "cell_type": "code",
|
5130 | 5203 | "metadata": {
|
5131 |
| - "id": "rVIKni0oLzEp", |
5132 |
| - "outputId": "d29c29eb-3b5f-4e01-a11b-cd5590ff872c", |
5133 | 5204 | "colab": {
|
5134 | 5205 | "base_uri": "https://localhost:8080/"
|
5135 |
| - } |
| 5206 | + }, |
| 5207 | + "id": "rVIKni0oLzEp", |
| 5208 | + "outputId": "d29c29eb-3b5f-4e01-a11b-cd5590ff872c" |
5136 | 5209 | },
|
5137 | 5210 | "execution_count": 9,
|
5138 | 5211 | "outputs": [
|
|
5206 | 5279 | ],
|
5207 | 5280 | "metadata": {
|
5208 | 5281 | "id": "arxzUdHrLBAS",
|
5209 |
| - "outputId": "9920a20c-32ad-4da8-e0c6-778ca362bb63", |
5210 | 5282 | "colab": {
|
5211 | 5283 | "base_uri": "https://localhost:8080/",
|
5212 | 5284 | "height": 108
|
5213 |
| - } |
| 5285 | + }, |
| 5286 | + "outputId": "9920a20c-32ad-4da8-e0c6-778ca362bb63" |
5214 | 5287 | },
|
5215 | 5288 | "execution_count": 7,
|
5216 | 5289 | "outputs": [
|
|
0 commit comments