{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Speaker Vector"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"This tutorial is available as an IPython notebook at [malaya-speech/example/speaker-vector](https://github.com/huseinzol05/malaya-speech/tree/master/example/speaker-vector).\n",
" \n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"This module is language independent, so it save to use on different languages. Pretrained models trained on multilanguages.\n",
" \n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"This is an application of malaya-speech Pipeline, read more about malaya-speech Pipeline at [malaya-speech/example/pipeline](https://github.com/huseinzol05/malaya-speech/tree/master/example/pipeline).\n",
" \n",
"
"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from malaya_speech import Pipeline\n",
"import malaya_speech\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### List available deep model"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:root:tested on VoxCeleb2 test set. Lower EER is better.\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Size (MB) | \n",
" Quantized Size (MB) | \n",
" Embedding Size | \n",
" EER | \n",
"
\n",
" \n",
" \n",
" \n",
" | deep-speaker | \n",
" 96.7 | \n",
" 24.40 | \n",
" 512.0 | \n",
" 0.21870 | \n",
"
\n",
" \n",
" | vggvox-v1 | \n",
" 70.8 | \n",
" 17.70 | \n",
" 1024.0 | \n",
" 0.14070 | \n",
"
\n",
" \n",
" | vggvox-v2 | \n",
" 43.2 | \n",
" 7.92 | \n",
" 512.0 | \n",
" 0.04450 | \n",
"
\n",
" \n",
" | speakernet | \n",
" 35.0 | \n",
" 8.88 | \n",
" 7205.0 | \n",
" 0.02122 | \n",
"
\n",
" \n",
"
\n",
"