Fairseq
English
Catalan
fdelucaf commited on
Commit
043797c
1 Parent(s): b0da741

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -35,7 +35,7 @@ Translate a sentence using python
35
  import ctranslate2
36
  import pyonmttok
37
  from huggingface_hub import snapshot_download
38
- model_dir = snapshot_download(repo_id="projecte-aina/mt-aina-en-ca", revision="main")
39
 
40
  tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
41
  tokenized=tokenizer.tokenize("Welcome to the Aina Project!")
@@ -89,7 +89,7 @@ The model was trained on a combination of the following datasets:
89
 
90
  #### Tokenization
91
 
92
- All data is tokenized using sentencepiece, using 50 thousand token sentencepiece model learned from the combination of all filtered training data.
93
  This model is included.
94
 
95
  #### Hyperparameters
 
35
  import ctranslate2
36
  import pyonmttok
37
  from huggingface_hub import snapshot_download
38
+ model_dir = snapshot_download(repo_id="projecte-aina/aina-translator-en-ca", revision="main")
39
 
40
  tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
41
  tokenized=tokenizer.tokenize("Welcome to the Aina Project!")
 
89
 
90
  #### Tokenization
91
 
92
+ All data is tokenized using sentencepiece, using 50 thousand token sentencepiece model learned from the combination of all filtered training data.
93
  This model is included.
94
 
95
  #### Hyperparameters