Upload tokenizer
Browse files- README.md +9 -9
- tokenizer_config.json +1 -2
- vocab.json +56 -0
README.md
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
-
license: cc-by-nc-4.0
|
4 |
base_model: facebook/mms-1b-all
|
5 |
-
tags:
|
6 |
-
- generated_from_trainer
|
7 |
datasets:
|
8 |
- common_voice_17_0
|
|
|
|
|
9 |
metrics:
|
10 |
- wer
|
11 |
- bleu
|
|
|
|
|
12 |
model-index:
|
13 |
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
|
14 |
results:
|
15 |
- task:
|
16 |
-
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
|
|
18 |
dataset:
|
19 |
name: common_voice_17_0
|
20 |
type: common_voice_17_0
|
@@ -22,12 +22,12 @@ model-index:
|
|
22 |
split: validation
|
23 |
args: ta
|
24 |
metrics:
|
25 |
-
-
|
26 |
-
type: wer
|
27 |
value: 0.45588302699729566
|
28 |
-
|
29 |
-
|
30 |
value: 0.30120570288375
|
|
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
1 |
---
|
|
|
|
|
2 |
base_model: facebook/mms-1b-all
|
|
|
|
|
3 |
datasets:
|
4 |
- common_voice_17_0
|
5 |
+
library_name: transformers
|
6 |
+
license: cc-by-nc-4.0
|
7 |
metrics:
|
8 |
- wer
|
9 |
- bleu
|
10 |
+
tags:
|
11 |
+
- generated_from_trainer
|
12 |
model-index:
|
13 |
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
|
14 |
results:
|
15 |
- task:
|
|
|
16 |
type: automatic-speech-recognition
|
17 |
+
name: Automatic Speech Recognition
|
18 |
dataset:
|
19 |
name: common_voice_17_0
|
20 |
type: common_voice_17_0
|
|
|
22 |
split: validation
|
23 |
args: ta
|
24 |
metrics:
|
25 |
+
- type: wer
|
|
|
26 |
value: 0.45588302699729566
|
27 |
+
name: Wer
|
28 |
+
- type: bleu
|
29 |
value: 0.30120570288375
|
30 |
+
name: Bleu
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
tokenizer_config.json
CHANGED
@@ -39,9 +39,8 @@
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
-
"processor_class": "Wav2Vec2Processor",
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
-
"target_lang": "tam-
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
"unk_token": "[UNK]",
|
47 |
"word_delimiter_token": "|"
|
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
|
|
42 |
"replace_word_delimiter_char": " ",
|
43 |
+
"target_lang": "tam-256",
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
45 |
"unk_token": "[UNK]",
|
46 |
"word_delimiter_token": "|"
|
vocab.json
CHANGED
@@ -111,6 +111,62 @@
|
|
111 |
"ௗ": 50,
|
112 |
"ഥ": 51
|
113 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
"tam-32": {
|
115 |
"&": 1,
|
116 |
"[PAD]": 53,
|
|
|
111 |
"ௗ": 50,
|
112 |
"ഥ": 51
|
113 |
},
|
114 |
+
"tam-256": {
|
115 |
+
"&": 1,
|
116 |
+
"[PAD]": 53,
|
117 |
+
"[UNK]": 52,
|
118 |
+
"_": 2,
|
119 |
+
"|": 0,
|
120 |
+
"ஃ": 3,
|
121 |
+
"அ": 4,
|
122 |
+
"ஆ": 5,
|
123 |
+
"இ": 6,
|
124 |
+
"ஈ": 7,
|
125 |
+
"உ": 8,
|
126 |
+
"ஊ": 9,
|
127 |
+
"எ": 10,
|
128 |
+
"ஏ": 11,
|
129 |
+
"ஐ": 12,
|
130 |
+
"ஒ": 13,
|
131 |
+
"ஓ": 14,
|
132 |
+
"ஔ": 15,
|
133 |
+
"க": 16,
|
134 |
+
"ங": 17,
|
135 |
+
"ச": 18,
|
136 |
+
"ஜ": 19,
|
137 |
+
"ஞ": 20,
|
138 |
+
"ட": 21,
|
139 |
+
"ண": 22,
|
140 |
+
"த": 23,
|
141 |
+
"ந": 24,
|
142 |
+
"ன": 25,
|
143 |
+
"ப": 26,
|
144 |
+
"ம": 27,
|
145 |
+
"ய": 28,
|
146 |
+
"ர": 29,
|
147 |
+
"ற": 30,
|
148 |
+
"ல": 31,
|
149 |
+
"ள": 32,
|
150 |
+
"ழ": 33,
|
151 |
+
"வ": 34,
|
152 |
+
"ஷ": 35,
|
153 |
+
"ஸ": 36,
|
154 |
+
"ஹ": 37,
|
155 |
+
"ா": 38,
|
156 |
+
"ி": 39,
|
157 |
+
"ீ": 40,
|
158 |
+
"ு": 41,
|
159 |
+
"ூ": 42,
|
160 |
+
"ெ": 43,
|
161 |
+
"ே": 44,
|
162 |
+
"ை": 45,
|
163 |
+
"ொ": 46,
|
164 |
+
"ோ": 47,
|
165 |
+
"ௌ": 48,
|
166 |
+
"்": 49,
|
167 |
+
"ௗ": 50,
|
168 |
+
"ഥ": 51
|
169 |
+
},
|
170 |
"tam-32": {
|
171 |
"&": 1,
|
172 |
"[PAD]": 53,
|