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: 0.4958060228262364
|
28 |
-
|
29 |
-
|
30 |
value: 0.2629057639184852
|
|
|
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: 0.4958060228262364
|
27 |
+
name: Wer
|
28 |
+
- type: bleu
|
29 |
value: 0.2629057639184852
|
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-64",
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
45 |
"unk_token": "[UNK]",
|
46 |
"word_delimiter_token": "|"
|
vocab.json
CHANGED
@@ -279,6 +279,62 @@
|
|
279 |
"ௗ": 50,
|
280 |
"ഥ": 51
|
281 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
282 |
"tam-8192": {
|
283 |
"&": 1,
|
284 |
"[PAD]": 53,
|
|
|
279 |
"ௗ": 50,
|
280 |
"ഥ": 51
|
281 |
},
|
282 |
+
"tam-64": {
|
283 |
+
"&": 1,
|
284 |
+
"[PAD]": 53,
|
285 |
+
"[UNK]": 52,
|
286 |
+
"_": 2,
|
287 |
+
"|": 0,
|
288 |
+
"ஃ": 3,
|
289 |
+
"அ": 4,
|
290 |
+
"ஆ": 5,
|
291 |
+
"இ": 6,
|
292 |
+
"ஈ": 7,
|
293 |
+
"உ": 8,
|
294 |
+
"ஊ": 9,
|
295 |
+
"எ": 10,
|
296 |
+
"ஏ": 11,
|
297 |
+
"ஐ": 12,
|
298 |
+
"ஒ": 13,
|
299 |
+
"ஓ": 14,
|
300 |
+
"ஔ": 15,
|
301 |
+
"க": 16,
|
302 |
+
"ங": 17,
|
303 |
+
"ச": 18,
|
304 |
+
"ஜ": 19,
|
305 |
+
"ஞ": 20,
|
306 |
+
"ட": 21,
|
307 |
+
"ண": 22,
|
308 |
+
"த": 23,
|
309 |
+
"ந": 24,
|
310 |
+
"ன": 25,
|
311 |
+
"ப": 26,
|
312 |
+
"ம": 27,
|
313 |
+
"ய": 28,
|
314 |
+
"ர": 29,
|
315 |
+
"ற": 30,
|
316 |
+
"ல": 31,
|
317 |
+
"ள": 32,
|
318 |
+
"ழ": 33,
|
319 |
+
"வ": 34,
|
320 |
+
"ஷ": 35,
|
321 |
+
"ஸ": 36,
|
322 |
+
"ஹ": 37,
|
323 |
+
"ா": 38,
|
324 |
+
"ி": 39,
|
325 |
+
"ீ": 40,
|
326 |
+
"ு": 41,
|
327 |
+
"ூ": 42,
|
328 |
+
"ெ": 43,
|
329 |
+
"ே": 44,
|
330 |
+
"ை": 45,
|
331 |
+
"ொ": 46,
|
332 |
+
"ோ": 47,
|
333 |
+
"ௌ": 48,
|
334 |
+
"்": 49,
|
335 |
+
"ௗ": 50,
|
336 |
+
"ഥ": 51
|
337 |
+
},
|
338 |
"tam-8192": {
|
339 |
"&": 1,
|
340 |
"[PAD]": 53,
|