auracaster/piper
3
0
Fork 0
mirror of https://github.com/pstrueb/piper.git synced 2026-04-16 13:25:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated model exporter notebook.

Browse Source
This commit is contained in:
Mateo Cedillo
2023-06-04 09:10:47 -05:00
parent c7c2343283
commit c5578a889a
1 changed files with 45 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
notebooks/piper_model_exporter.ipynb
View File

@@ -5,7 +5,7 @@
"colab": {
"provenance": [],
"gpuType": "T4",
"authorship_tag": "ABX9TyOyCiCt4X4oZWyqzQ2fAafX",
"authorship_tag": "ABX9TyNKVcsLxVm78BeU3TIFeDMa",
"include_colab_link": true
},
"kernelspec": {
@@ -52,7 +52,6 @@
"!git clone https://github.com/rhasspy/piper\n",
"%cd /content/piper/src/python\n",
"!pip install --upgrade pip\n",
"!pip install --upgrade wheel setuptools\n",
"!pip install cython>=0.29.0 espeak-phonemizer>=1.1.0 librosa>=0.9.2 numpy>=1.19.0 pytorch-lightning~=1.7.0 torch~=1.11.0\n",
"!pip install onnx onnxruntime-gpu\n",
"!bash build_monotonic_align.sh\n",
@@ -66,9 +65,13 @@
"#@title Voice package generation section\n",
"%cd /content/piper/src/python\n",
"import os\n",
"import ipywidgets as widgets\n",
"from IPython.display import display\n",
"import json\n",
"from google.colab import output\n",
"#@markdown #### Download:\n",
"#@markdown **Google Drive model ID:**\n",
"model_id = \"\" #@param {type:\"string\"}\n",
"model_id = \"1LQ8CY8stAhk6aK2HbDxNOvff8vT0q7Jr+\" #@param {type:\"string\"}\n",
"#@markdown **Config.json Google Drive ID**\n",
"config_id = \"1-7qJ-Aw8OmqKgxxG8o_onU_Rwn0xfIOj\" #@param {type:\"string\"}\n",
"#@markdown ---\n",
@@ -82,15 +85,46 @@
"export_voice_path = \"/content/project/voice-\"+export_voice_name\n",
"packages_path = \"/content/project/packages\"\n",
"if not os.path.exists(export_voice_path):\n",
" os.makedirs(export_voice_path)\n",
" os.makedirs(export_voice_path)\n",
"if not os.path.exists(packages_path):\n",
" os.makedirs(packages_path)\n",
"!gdown \"{model_id}\" -O /content/project/model.ckpt\n",
"!gdown \"{config_id}\" -O \"{export_voice_path}/{export_voice_name}.onnx.json\"\n",
"!python -m piper_train.export_onnx \"/content/project/model.ckpt\" \"{export_voice_path}/{export_voice_name}.onnx\"\n",
"print(\"compressing...\")\n",
"%cd /content/project\n",
"!tar -czvf \"{packages_path}/voice-{export_voice_name}.tar.gz\" \"voice-{export_voice_name}\""
" os.makedirs(packages_path)\n",
"print(\"Downloading model and his config...\")\n",
"!gdown -q \"{model_id}\" -O /content/project/model.ckpt\n",
"!gdown -q \"{config_id}\" -O \"{export_voice_path}/{export_voice_name}.onnx.json\"\n",
"#@markdown **Do you want to write a model card?**\n",
"write_model_card = True #@param {type:\"boolean\"}\n",
"if write_model_card:\n",
" with open(f\"{export_voice_path}/{export_voice_name}.onnx.json\", \"r\") as file:\n",
" config = json.load(file)\n",
" sample_rate = config[\"audio\"][\"sample_rate\"]\n",
" num_speakers = config[\"num_speakers\"]\n",
" output.eval_js('new Audio(\"https://github.com/rmcpantoja/piper/raw/master/notebooks/waiting.wav?raw=true\").play()')\n",
" text_area = widgets.Textarea(\n",
" description = \"fill in this following template and press start to generate the voice package\",\n",
" value=f'# Model card for {voice_name} ({quality})\\n\\n* Language: {language} (normaliced)\\n* Speakers: {num_speakers}\\n* Quality: {quality}\\n* Samplerate: {sample_rate}Hz\\n\\n## Dataset\\n\\n* URL: \\n* License: \\n\\n## Training\\n\\nTrained from scratch.\\nOr finetuned from: ',\n",
" layout=widgets.Layout(width='500px', height='200px')\n",
" )\n",
" button = widgets.Button(description='Start')\n",
"\n",
" def create_model_card(button):\n",
" model_card_text = text_area.value.strip()\n",
" with open(f'{export_voice_path}/MODEL_CARD', 'w') as file:\n",
" file.write(model_card_text)\n",
" text_area.close()\n",
" button.close()\n",
" output.clear()\n",
" output.eval_js('new Audio(\"https://github.com/rmcpantoja/piper/blob/master/notebooks/starting.wav?raw=true\").play()')\n",
" start_process()\n",
"\n",
" button.on_click(create_model_card)\n",
"\n",
" display(text_area, button)\n",
"\n",
"def start_process():\n",
" !python -m piper_train.export_onnx \"/content/project/model.ckpt\" \"{export_voice_path}/{export_voice_name}.onnx\"\n",
" print(\"compressing...\")\n",
" !tar -czvf \"{packages_path}/voice-{export_voice_name}.tar.gz\" -C \"{export_voice_path}\" .\n",
" output.eval_js('new Audio(\"https://github.com/rmcpantoja/piper/raw/master/notebooks/success.wav?raw=true\").play()')"
],
"metadata": {
"cellView": "form",