experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Cosmetic changes

Browse Source
This commit is contained in:
Josh Meyer 2021-09-15 07:57:53 -04:00
parent f6a64e7dd8
commit 8a3cea8b6d
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
notebooks/train_your_first_coqui_STT_model.ipynb
View File

@ -54,9 +54,9 @@
"2. the **size** of that audio file\n", "2. the **size** of that audio file\n",
"3. the **transcript** of that audio file.\n", "3. the **transcript** of that audio file.\n",
"\n", "\n",
"Formatting the audio and transcript isn't too difficult in this case. We define a custom data importer called `download_sample_data()` which does all the work. If you have a custom dataset, you will probably want to write a custom data importer.\n", "Formatting the audio and transcript isn't too difficult in this case. We define `download_sample_data()` which does all the work. If you have a custom dataset, you will want to write a custom data importer.\n",
"\n", "\n",
"**Second things second**: we want an alphabet. The output layer of a typical* 🐸 STT model represents letters in the alphabet, and you should specify this alphabet before training. Let's download an English alphabet from Coqui and use that.\n", "**Second things second**: we want an alphabet. The output layer of a typical* 🐸 STT model represents letters in the alphabet. Let's download an English alphabet from Coqui and use that.\n",
"\n", "\n",
"*_If you are working with languages with large character sets (e.g. Chinese), you can set `bytes_output_mode=True` instead of supplying an `alphabet.txt` file. In this case, the output layer of the STT model will correspond to individual UTF-8 bytes instead of individual characters._" "*_If you are working with languages with large character sets (e.g. Chinese), you can set `bytes_output_mode=True` instead of supplying an `alphabet.txt` file. In this case, the output layer of the STT model will correspond to individual UTF-8 bytes instead of individual characters._"
] ]
@ -98,7 +98,7 @@
"id": "96e8b708", "id": "96e8b708",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Take a look at the data (*Optional* )" "### 👀 Take a look at the data"
] ]
}, },
{ {
@ -150,7 +150,7 @@
" dev_files=[\"english/ldc93s1.csv\"],\n", " dev_files=[\"english/ldc93s1.csv\"],\n",
" 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=200,\n",
" epochs=100,\n", " epochs=100,\n",
")" ")"
] ]
@ -160,7 +160,7 @@
"id": "799c1425", "id": "799c1425",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### View all Config settings (*Optional*) " "### 👀 View all Config settings"
] ]
}, },
{ {