infinitejoy
commited on
Commit
·
48c844e
1
Parent(s):
efaa714
add tokenizer
Browse files- added_tokens.json +1 -1
- log_mozilla-foundation_common_voice_7_0_sah_test_predictions.txt +0 -0
- log_mozilla-foundation_common_voice_7_0_sah_test_targets.txt +0 -0
- mozilla-foundation_common_voice_7_0_sah_test_eval_results.txt +2 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- vocab.json +1 -1
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<s>":
|
|
|
1 |
+
{"<s>": 51, "</s>": 52}
|
log_mozilla-foundation_common_voice_7_0_sah_test_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
log_mozilla-foundation_common_voice_7_0_sah_test_targets.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mozilla-foundation_common_voice_7_0_sah_test_eval_results.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
WER: 0.4419661883790311
|
2 |
+
CER: 0.102713365695167
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
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}
|
|
|
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
CHANGED
@@ -1 +1 @@
|
|
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": "./
|
|
|
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
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"`": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "³": 28, "á": 29, "ä": 30, "é": 31, "í": 32, "ó": 33, "ô": 34, "ö": 35, "ú": 36, "ý": 37, "č": 38, "ď": 39, "ĺ": 40, "ľ": 41, "ň": 42, "ŕ": 43, "š": 44, "ť": 45, "ž": 46, "̌": 47, "„": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}
|