add tokenizer

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 40, "</s>": 41}

runs/Jan03_14-30-20_5b60acbd6673/1672756342.4463282/events.out.tfevents.1672756342.5b60acbd6673.3791.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417d856abacfdabbeb057a89f8a7d7de3d0c69c01d76d65143dd1f5bb1771644
+size 4534

runs/Jan03_14-30-20_5b60acbd6673/events.out.tfevents.1672756342.5b60acbd6673.3791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2c005d97d9f8d7141a0f78ef5f733fcb086db24521a357854756155793e736
+size 4189

runs/Jan03_14-32-49_5b60acbd6673/1672756491.7273748/events.out.tfevents.1672756491.5b60acbd6673.3791.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f892dbdcbcc1ee7918ef654975a3f519b812420adab441fb892f51ee2c899e3
+size 4534

runs/Jan03_14-32-49_5b60acbd6673/events.out.tfevents.1672756491.5b60acbd6673.3791.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3003f7d07f80877005c8db80a518c7c976a3994c4c8d5eb7d6facb7cc5b3ad06
+size 4189

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"a": 0, "aː": 1, "b": 2, "d": 3, "e": 4, "eː": 5, "f": 6, "h": 7, "i": 8, "iː": 9, "j": 10, "k": 11, "kʰ": 12, "l": 13, "m": 14, "n": 15, "o": 16, "oː": 17, "p": 18, "pʰ": 19, "r": 20, "s": 21, "t": 22, "t͡ɕ": 23, "t͡ɕʰ": 24, "u": 25, "uː": 26, "w": 27, "ŋ": 28, "ɔ": 29, "ɔː": 30, "ɛ": 31, "ɛː": 32, "ɤ": 33, "ɤː": 34, "ɯ": 35, "ɯː": 36, "ʔ": 37, "[UNK]": 38, "[PAD]": 39}