add tokenizer

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd20c408ec4568361d32b41080e3f6fa5b82895135bd25c2747b2c145e42d07b
+size 1057690

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e29ae4dc88885934c6c9de3aa93755484485d8b4eb545ee5f46821621c11671
+size 813128

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "Helsinki-NLP/opus-mt-hi-en",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "hi",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}