Actualizando modelos

README.md

@@ -2,7 +2,7 @@
 git : [DeepSpeech](https://github.com/mozilla/DeepSpeech)
 
 ## Requisitos:
-* Python 3.6
+* Python 3.5 o 3.6
 * Linux o Mac
 
 Algunos comandos:

models/alphabet.txt

@@ -12,6 +12,8 @@ f
 g
 h
 i
+j
+k
 l
 m
 n
@@ -23,5 +25,9 @@ s
 t
 u
 v
+w
+x
+y
 z
+'
 # The last (non-comment) line needs to end with a newline.

vocabulary_generator.ipynb

@@ -15,7 +15,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import csv"
+    "import csv\n",
+    "import re"
    ]
   },
   {
@@ -43,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -52,7 +53,8 @@
     "file = open('vocabulary_es.txt','w') \n",
     "with open('D:/SpeechServices/data/spanish-single-speaker-speech-dataset/transcript.txt',encoding='utf-8') as txtfile:\n",
     "    for line in txtfile:\n",
-    "        file.write(line.split('|')[1])\n",
+    "        text = re.sub('\\W+', '', line.split('|')[1])\n",
+    "        file.write(text)\n",
     "file.close()"
    ]
   },