More notebook work

This commit is contained in:
Josh Meyer 2021-09-15 06:54:25 -04:00
parent 0e8920ed63
commit 2729da33a8
3 changed files with 33 additions and 22 deletions

View File

@ -147,7 +147,7 @@
" alphabet_config_path=\"russian/alphabet.txt\",\n", " alphabet_config_path=\"russian/alphabet.txt\",\n",
" train_files=[\"russian/ru.csv\"],\n", " train_files=[\"russian/ru.csv\"],\n",
" dev_files=[\"russian/ru.csv\"],\n", " dev_files=[\"russian/ru.csv\"],\n",
" epochs=200,\n", " epochs=100,\n",
" load_cudnn=True,\n", " load_cudnn=True,\n",
")" ")"
] ]

View File

@ -92,21 +92,32 @@
], ],
"id": "be5fe49c" "id": "be5fe49c"
}, },
{ {
"cell_type": "code", "cell_type": "code",
"metadata": { "execution_count": null,
"scrolled": true, "id": "608d203f",
"id": "53945462" "metadata": {},
}, "outputs": [],
"source": [ "source": [
"### Download pre-formatted Common Voice data\n", "### Download pre-formatted Common Voice data\n",
"! wget https://coqui-ai-public-data.s3.amazonaws.com/cv/7.0/kk-data.tar\n", "import os\n",
"! tar -xf kk-data.tar" "import tarfile\n",
], "from coqui_stt_training.util.downloader import maybe_download\n",
"id": "53945462", "\n",
"execution_count": null, "def download_preformatted_data():\n",
"outputs": [] " if not os.path.exists(\"data/sr-data\"):\n",
}, " maybe_download(\"sr-data.tar\", \"data/\", \"https://coqui-ai-public-data.s3.amazonaws.com/cv/7.0/sr-data.tar\")\n",
" print('\\nNo extracted data found. Extracting now...')\n",
" tar = tarfile.open(\"data/sr-data.tar\", mode=\"r:\")\n",
" tar.extractall(\"data/\")\n",
" tar.close()\n",
" else:\n",
" print('Found \"data/sr-data\" - not extracting.')\n",
"\n",
"# Download + extract Common Voice data\n",
"download_preformatted_data()"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
@ -123,8 +134,8 @@
"id": "fa2aec77" "id": "fa2aec77"
}, },
"source": [ "source": [
"! ls kk-data\n", "! ls data/sr-data\n",
"! wc -l kk-data/*.csv" "! wc -l data/sr-data/*.csv"
], ],
"id": "fa2aec77", "id": "fa2aec77",
"execution_count": null, "execution_count": null,
@ -155,9 +166,9 @@
"from coqui_stt_training.util.config import initialize_globals_from_args\n", "from coqui_stt_training.util.config import initialize_globals_from_args\n",
"\n", "\n",
"initialize_globals_from_args(\n", "initialize_globals_from_args(\n",
" train_files=[\"kk-data/train.csv\"],\n", " train_files=[\"data/sr-data/train.csv\"],\n",
" dev_files=[\"kk-data/dev.csv\"],\n", " dev_files=[\"data/sr-data/dev.csv\"],\n",
" test_files=[\"kk-data/test.csv\"],\n", " test_files=[\"data/sr-data/test.csv\"],\n",
" load_train=\"init\",\n", " load_train=\"init\",\n",
" n_hidden=200,\n", " n_hidden=200,\n",
" epochs=1,\n", " epochs=1,\n",

View File

@ -151,7 +151,7 @@
" test_files=[\"english/ldc93s1.csv\"],\n", " test_files=[\"english/ldc93s1.csv\"],\n",
" load_train=\"init\",\n", " load_train=\"init\",\n",
" n_hidden=100,\n", " n_hidden=100,\n",
" epochs=200,\n", " epochs=100,\n",
")" ")"
] ]
}, },