auracaster/piper
3
0
Fork 0
mirror of https://github.com/pstrueb/piper.git synced 2026-06-04 19:07:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed notebook.

Browse Source
This commit is contained in:
Mateo Cedillo
2023-05-25 21:30:39 -05:00
parent 9e6d2dcbfe
commit 684b625160
1 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/piper_multilingual_training_notebook.ipynb
+16 -14
View File
@@ -4,7 +4,8 @@
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyPovMyxp8xorYRHeQp1RAP2",
"gpuType": "T4",
"authorship_tag": "ABX9TyOhGmWaOcJ8eRFW1QnG2XyK",
"include_colab_link": true
},
"kernelspec": {
@@ -13,7 +14,9 @@
},
"language_info": {
"name": "python"
}
},
"accelerator": "GPU",
"gpuClass": "standard"
},
"cells": [
{
@@ -140,7 +143,7 @@
"%cd /content/dataset\n",
"!mkdir /content/dataset/wavs\n",
"#@markdown ### Audio dataset path to unzip\n",
"zip_path = \"/content/drive/MyDrive/Fakeyou/odal_castilian/wavs16k.zip\" #@param {type:\"string\"}\n",
"zip_path = \"/content/drive/MyDrive/Fakeyou/aldEnhanced/wavs.zip\" #@param {type:\"string\"}\n",
"!unzip \"{zip_path}\" -d /content/dataset/wavs\n",
"#@markdown ---"
],
@@ -221,7 +224,7 @@
"dataset_format = \"ljspeech\" #@param [\"ljspeech\", \"mycroft\"]\n",
"#@markdown ---\n",
"#@markdown ### Select the sample rate of the dataset\n",
"sample_rate = \"16000\" #@param [\"16000\", \"22050\"]\n",
"sample_rate = \"22050\" #@param [\"16000\", \"22050\"]\n",
"#@markdown ---\n",
"%cd /content/piper/src/python\n",
"!python -m piper_train.preprocess \\\n",
@@ -252,17 +255,17 @@
"if finetune:\n",
" ft_command = '--resume_from_checkpoint \"/content/pretrained.ckpt\" '\n",
" try:\n",
" with open('/CONTENT/PIPER/NOTEBOOKS/pretrained_models.json') as f:\n",
" with open('/content/piper/notebooks/pretrained_models.json') as f:\n",
" pretrained_models = json.load(f)\n",
" if final_language in pretrained_models:\n",
" models = pretrained_models[final_language]\n",
" model_options = [(model_name, model_url) for model_name, model_url in models.items()]\n",
" model_options = [(model_name, model_name) for model_name, model_url in models.items()]\n",
" model_dropdown = widgets.Dropdown(description = \"Choose pretrained model\", options=model_options)\n",
" download_button = widgets.Button(description=\"Download\")\n",
" def download_model(btn):\n",
" model_name, model_url = model_dropdown.value\n",
" file_id = model_url.split('/')[-2]\n",
" !gdown {file_id} -O \"/content/pretrained.ckpt\"\n",
" model_name = model_dropdown.value\n",
" model_url = pretrained_models[final_language][model_name]\n",
" !gdown \"{model_url}\" -O \"/content/pretrained.ckpt\"\n",
"\n",
" download_button.on_click(download_model)\n",
" display(model_dropdown, download_button)\n",
@@ -273,7 +276,7 @@
"else:\n",
" ft_command = \"\"\n",
"#@makrdown ### Choose batch size based on this dataset\n",
"batch_size = 8 #@param {type:\"integer\"}\n",
"batch_size = 16 #@param {type:\"integer\"}\n",
"#@markdown ---\n",
"#@markdown ### Validation split\n",
"validation_split = 0.03 #@param {type:\"number\"}\n",
@@ -284,13 +287,13 @@
"#@markdown * low - 16Khz audio, 15-20M params\n",
"#@markdown * medium - 22.05Khz audio, 15-20 params\n",
"#@markdown * high - 22.05Khz audio, 28-32M params\n",
"quality = \"x-low\" #@param [\"high\", \"low\", \"medium\", \"x-low\"]\n",
"quality = \"x-low\" #@param [\"high\", \"x-low\", \"medium\"]\n",
"#@markdown ---\n",
"#@markdown ### For how many steps to save training checkpoints?\n",
"checkpoint_epochs = 25 #@param {type:\"integer\"}\n",
"#@markdown ---\n",
"#@markdown ### Step interval to generate model samples\n",
"log_every_n_steps = 1000 #@param {type:\"integer\"}\n",
"log_every_n_steps = 250 #@param {type:\"integer\"}\n",
"#@markdown ---\n",
"#@markdown ### training epochs\n",
"max_epochs = 5000 #@param {type:\"integer\"}\n",
@@ -336,11 +339,10 @@
" --num_sanity_val_steps 1000 \\\n",
" --log_every_n_steps {log_every_n_steps} \\\n",
" --max_epochs {max_epochs} \\\n",
" {ft-command}\\\n",
" {ft_command}\\\n",
" --precision 32"
],
"metadata": {
"cellView": "form",
"id": "X4zbSjXg2J3N"
},
"execution_count": null,