Kartikeyssj2 commited on
Commit
c14d52f
·
1 Parent(s): 7365efc
Files changed (2) hide show
  1. download_vocabulary.py +12 -0
  2. main.py +1 -1
download_vocabulary.py ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import requests
2
+
3
+
4
+ def download_word_list():
5
+ print("Downloading English word list...")
6
+ url = "https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt"
7
+ response = requests.get(url)
8
+ words = set(response.text.split())
9
+ print("Word list downloaded.")
10
+ return words
11
+
12
+ english_words = download_word_list()
main.py CHANGED
@@ -18,7 +18,6 @@ app = FastAPI()
18
  # Load Wav2Vec2 tokenizer and model
19
  tokenizer = Wav2Vec2Tokenizer.from_pretrained("./models/tokenizer")
20
  model = Wav2Vec2ForCTC.from_pretrained("./models/model")
21
- english_words = download_word_list()
22
 
23
 
24
  # Function to download English word list
@@ -30,6 +29,7 @@ def download_word_list():
30
  print("Word list downloaded.")
31
  return words
32
 
 
33
 
34
  # Function to count correctly spelled words in text
35
  def count_spelled_words(text, word_list):
 
18
  # Load Wav2Vec2 tokenizer and model
19
  tokenizer = Wav2Vec2Tokenizer.from_pretrained("./models/tokenizer")
20
  model = Wav2Vec2ForCTC.from_pretrained("./models/model")
 
21
 
22
 
23
  # Function to download English word list
 
29
  print("Word list downloaded.")
30
  return words
31
 
32
+ english_words = download_word_list()
33
 
34
  # Function to count correctly spelled words in text
35
  def count_spelled_words(text, word_list):