{
"cells": [
{
"cell_type": "markdown",
"source": [
"#Latviešu valodas runas atpazīšana\n",
"\n",
"Šajā bloknotā ir rīki latviešu valodas runas atpazīšanai. Tiek izmantots LU MII AiLab izveidotais [runas atpazīšanas modelis](https://huggingface.co/AiLab-IMCS-UL/whisper-large-v3-lv-late-cv17), kas veidots izmantojot [Balsu talkā](https://balsutalka.lv/) savāktos datus.\n",
"\n",
"Lai veiktu runas atpazīšanu audio failā sekojiet zemāk uzskaitītajiem soļiem."
],
"metadata": {
"id": "zZBBTnW-aThp"
}
},
{
"cell_type": "markdown",
"source": [
"##1. Nomainiet izpildlaika veidu uz T4 GPU\n",
"\n",
"Lai to izdarītu galvenajā izvēlnē šīs lapas augšpusē ejiet uz `Izpildlaiks` -> `Mainīt izpildlaika veidu` un izvēlieties `T4 GPU`\n",
"\n",
""
],
"metadata": {
"id": "GALJps6fDlQD"
}
},
{
"cell_type": "code",
"source": [
"#@title 2. Nospiediet uz atskaņošanas pogas, lai ielādētu nepieciešamos rīkus.\n",
"\n",
"import ipywidgets as widgets\n",
"from IPython.display import clear_output\n",
"import torch\n",
"from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline\n",
"\n",
"uploader = widgets.FileUpload(description='Izvēlieties audio', accept='audio/*', multiple=False)\n",
"# uploader = widgets.FileUpload(multiple=False)\n",
"display(uploader)"
],
"metadata": {
"id": "zLDYIFciCMTw",
"cellView": "form"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"##3. Izvēlieties audio failu\n",
"Pēc rīku ielādes parādīsies poga \"Izvēlieties audio\", nospiediet to un izvēlieties audio failu kurā atpazīt latviešu valodas runu."
],
"metadata": {
"id": "QxsuN4r0QGnl"
}
},
{
"cell_type": "code",
"source": [
"# @title 4. Palaidiet runas atpazīšanas procesu\n",
"\n",
"if len(uploader.data) == 0:\n",
" display(widgets.HTML(\n",
" value=\"<h3>Audio fails nav izvēlēts, lūdzu izvēlieties audio failu!</h3>\"\n",
" ))\n",
"else:\n",
"\n",
" display(widgets.HTML(\n",
" value=\"<h3>Notiek ielāde...</h3>\"\n",
" ))\n",
"\n",
" device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
" torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32\n",
"\n",
" model_id = \"AiLab-IMCS-UL/whisper-large-v3-lv-late-cv17\"\n",
"\n",
" model = AutoModelForSpeechSeq2Seq.from_pretrained(\n",
" model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=False, use_safetensors=True\n",
" ).to(device)\n",
"\n",
" processor = AutoProcessor.from_pretrained(model_id)\n",
"\n",
" pipe = pipeline(\n",
" \"automatic-speech-recognition\",\n",
" generate_kwargs={\"language\": \"latvian\", \"task\": \"transcribe\"},\n",
" model=model,\n",
" tokenizer=processor.tokenizer,\n",
" feature_extractor=processor.feature_extractor,\n",
" max_new_tokens=225,\n",
" chunk_length_s=30,\n",
" batch_size=16,\n",
" return_timestamps=False,\n",
" torch_dtype=torch_dtype,\n",
" device=device,\n",
" )\n",
"\n",
" clear_output()\n",
"\n",
" display(widgets.HTML(\n",
" value=\"<h3>Notiek audio atpazīšana...</h3>\"\n",
" ))\n",
"\n",
" result = pipe(uploader.data[0])\n",
"\n",
" with open('transcript.txt', 'w') as f:\n",
" f.write(result[\"text\"])\n",
"\n",
" result_widget = widgets.HTML(\n",
" value=result[\"text\"]\n",
" )\n",
"\n",
" clear_output()\n",
"\n",
" display(widgets.HTML(\n",
" value=result[\"text\"]\n",
" ))"
],
"metadata": {
"cellView": "form",
"id": "_6ovCwwqC6SM"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## 5. Saglabājiet audio failā atpazīto tekstu\n",
"Pēc audio faila apstrādes tajā atpazītais teksts tiks izdrukāts zem ceturtā soļa šūnas, kā arī tas tiks saglabāts teksta failā `transcript.txt`. Lai apskatītu šo failu uzklikšķiniet uz mapītes ikonas ekrāna sānā.\n",
"\n",
"\n"
],
"metadata": {
"id": "PLqlD2N7STNq"
}
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}