speech-test
commited on
Commit
•
2922828
1
Parent(s):
20f885c
Tokenizer-less model
Browse files- .gitignore +3 -0
- preprocessor_config.json +1 -1
- special_tokens_map.json +0 -1
- tokenizer_config.json +0 -1
- vocab.json +0 -1
.gitignore
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
special_tokens_map.json
|
2 |
+
tokenizer_config.json
|
3 |
+
vocab.json
|
preprocessor_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
-
"padding_value": 0,
|
7 |
"return_attention_mask": false,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
"return_attention_mask": false,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
|
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "return_attention_mask": false, "do_normalize": true, "model_max_length": 9223372036854775807, "special_tokens_map_file": "/home/crocopie/.cache/huggingface/transformers/208086b2429fa2ba5b196810c1bcd7d61e2c8d4afd65d05d0670096d735fd5bb.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "facebook/wav2vec2-base-960h", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
vocab.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}
|
|
|
|