upendrawappgo commited on
Commit
0a719f5
1 Parent(s): d17032c

Upload tokenizer

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. README.md +1 -1
  3. source.spm +0 -0
  4. special_tokens_map.json +5 -0
  5. target.spm +3 -0
  6. tokenizer_config.json +38 -0
  7. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ target.spm filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: Helsinki-NLP/opus-mt-en-hi
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: englishtohinditranslator
8
  results: []
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_keras_callback
5
+ base_model: Helsinki-NLP/opus-mt-en-hi
6
  model-index:
7
  - name: englishtohinditranslator
8
  results: []
source.spm ADDED
Binary file (812 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5529d3a72f8c1d5f7e357f1b6fd30e3cf58f6e1ba0401db135a118ac92f4a76
3
+ size 1067935
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "61949": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "eng",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "hin",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff