add readme

README.md

@@ -0,0 +1,13 @@
+---
+language:
+- km
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- robust-speech-event
+- km
+datasets:
+model-index:
+- name: ''
+  results: []
+---

train_tr.ipynb

@@ -3,7 +3,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "3fa7516b",
+   "id": "89ce602d",
    "metadata": {
     "collapsed": true,
     "jupyter": {
@@ -783,20 +783,10 @@
     "pip install jiwer"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "09a1f5ea",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "c57800bb",
+   "id": "fcf5fa8d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -808,7 +798,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "98314e83",
+   "id": "e4e73fe4",
    "metadata": {},
    "source": [
     "### Common Voice Dataset"
@@ -817,7 +807,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "c9e549d0",
+   "id": "6151b4f2",
    "metadata": {},
    "outputs": [
     {
@@ -837,7 +827,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "c1ca3246",
+   "id": "c95a7685",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -848,7 +838,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7574225f",
+   "id": "c59e9e5f",
    "metadata": {},
    "source": [
     "### Clean Up the Text"
@@ -857,7 +847,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "af63fb74",
+   "id": "457e9338",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -873,7 +863,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "e1714034",
+   "id": "67fef1ed",
    "metadata": {},
    "outputs": [
     {
@@ -913,7 +903,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "d348cf4a",
+   "id": "63b5ce79",
    "metadata": {},
    "outputs": [
     {
@@ -938,7 +928,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "53070ed8",
+   "id": "df14e4c1",
    "metadata": {},
    "source": [
     "### Build Character"
@@ -947,7 +937,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "dc3b3351",
+   "id": "2f1bfdb5",
    "metadata": {},
    "outputs": [
     {
@@ -995,7 +985,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "ccd38414",
+   "id": "adf632a9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1006,7 +996,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "1eb8cfd7",
+   "id": "4f929bce",
    "metadata": {},
    "outputs": [
     {
@@ -1024,7 +1014,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "40088296",
+   "id": "9d7976c6",
    "metadata": {},
    "outputs": [
     {
@@ -1051,7 +1041,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "cc6882a1",
+   "id": "4d39c58d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1062,7 +1052,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "27df2a9d",
+   "id": "94293ddc",
    "metadata": {},
    "source": [
     "# Tokenizer"
@@ -1071,7 +1061,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "0d5cdfa3",
+   "id": "3cc51841",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1083,7 +1073,7 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "id": "fb3a2f1c",
+   "id": "d4ef2d6b",
    "metadata": {},
    "outputs": [
     {
@@ -1103,7 +1093,7 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "id": "52203070",
+   "id": "45b4d37c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1120,7 +1110,7 @@
   {
    "cell_type": "code",
    "execution_count": 27,
-   "id": "ac38e29c",
+   "id": "e49f0d0d",
    "metadata": {},
    "outputs": [
     {
@@ -1160,7 +1150,7 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "id": "caba15f7",
+   "id": "5278f944",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1171,7 +1161,7 @@
   {
    "cell_type": "code",
    "execution_count": 143,
-   "id": "040ba517",
+   "id": "1a345bd9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1182,7 +1172,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "id": "06f8aad7",
+   "id": "50a52463",
    "metadata": {},
    "outputs": [
     {
@@ -1208,7 +1198,7 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "id": "2c485e01",
+   "id": "43330076",
    "metadata": {},
    "outputs": [
     {
@@ -1255,7 +1245,7 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "id": "8e1df31f",
+   "id": "54926718",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1277,7 +1267,7 @@
   {
    "cell_type": "code",
    "execution_count": 24,
-   "id": "88b304c0",
+   "id": "0a348aa0",
    "metadata": {},
    "outputs": [
     {
@@ -1311,7 +1301,7 @@
   {
    "cell_type": "code",
    "execution_count": 41,
-   "id": "5a9767e7",
+   "id": "142e5d79",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1323,7 +1313,7 @@
   {
    "cell_type": "code",
    "execution_count": 25,
-   "id": "df2feb3b",
+   "id": "310cdbb1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1383,7 +1373,7 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "id": "bf081d03",
+   "id": "6cff622b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1393,7 +1383,7 @@
   {
    "cell_type": "code",
    "execution_count": 27,
-   "id": "2059e2de",
+   "id": "df12cc5b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1404,7 +1394,7 @@
   {
    "cell_type": "code",
    "execution_count": 28,
-   "id": "ac4bb898",
+   "id": "8b25005a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1428,7 +1418,7 @@
   {
    "cell_type": "code",
    "execution_count": 29,
-   "id": "43669353",
+   "id": "a7ac7d14",
    "metadata": {},
    "outputs": [
     {
@@ -1462,7 +1452,7 @@
   {
    "cell_type": "code",
    "execution_count": 30,
-   "id": "f6a6f61e",
+   "id": "352fb742",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1472,7 +1462,7 @@
   {
    "cell_type": "code",
    "execution_count": 31,
-   "id": "54b7d33d",
+   "id": "ae38b1c1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1499,7 +1489,7 @@
   {
    "cell_type": "code",
    "execution_count": 32,
-   "id": "929dc96c",
+   "id": "d60948cc",
    "metadata": {},
    "outputs": [
     {
@@ -1527,7 +1517,7 @@
   {
    "cell_type": "code",
    "execution_count": 33,
-   "id": "3460b4cd",
+   "id": "6b20f77c",
    "metadata": {},
    "outputs": [
     {
@@ -1751,7 +1741,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "df904372",
+   "id": "f580e49e",
    "metadata": {},
    "outputs": [],
    "source": []