akanksha-b14
commited on
Commit
•
994b64a
1
Parent(s):
c799153
add model
Browse files- added_tokens.json +1 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 29, "</s>": 30}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +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}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "processor_class": "Wav2Vec2Processor", "special_tokens_map_file": "./wav2vec2-base/special_tokens_map.json", "name_or_path": "./wav2vec2-base", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"m": 0, "q": 1, "r": 2, "h": 3, "o": 4, "v": 5, "s": 6, "w": 7, "b": 8, "u": 9, "j": 10, "c": 11, "z": 12, "y": 13, "a": 14, "e": 15, "i": 16, "p": 17, "l": 18, "g": 19, "n": 20, "d": 22, "k": 23, "x": 24, "f": 25, "t": 26, "|": 21, "[UNK]": 27, "[PAD]": 28}
|