Training in progress, step 5000
Browse files- added_tokens.json +0 -4
- pytorch_model.bin +1 -1
- runs/Dec01_07-36-04_a7d74671a65e/events.out.tfevents.1701416165.a7d74671a65e.1467.0 +3 -0
- special_tokens_map.json +35 -12
- tokenizer_config.json +12 -20
- training_args.bin +1 -1
added_tokens.json
CHANGED
@@ -1,10 +1,6 @@
|
|
1 |
{
|
2 |
-
"</s>": 2,
|
3 |
"<ctc_blank>": 80,
|
4 |
"<mask>": 79,
|
5 |
-
"<pad>": 1,
|
6 |
-
"<s>": 0,
|
7 |
-
"<unk>": 3,
|
8 |
"ஃ": 81,
|
9 |
"அ": 82,
|
10 |
"ஆ": 83,
|
|
|
1 |
{
|
|
|
2 |
"<ctc_blank>": 80,
|
3 |
"<mask>": 79,
|
|
|
|
|
|
|
4 |
"ஃ": 81,
|
5 |
"அ": 82,
|
6 |
"ஆ": 83,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 578029306
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24e7c178ab6a7c83dce17c0583514e0472c4223b0893b31fcc0b3a460cee20f3
|
3 |
size 578029306
|
runs/Dec01_07-36-04_a7d74671a65e/events.out.tfevents.1701416165.a7d74671a65e.1467.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31e8e74e66f8c45f4df028bd437f149fccfaa89ed1b35683baaaf18c14123fa0
|
3 |
+
size 38463
|
special_tokens_map.json
CHANGED
@@ -1,14 +1,37 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"<s>",
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
"
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": true,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": true,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": true,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "<mask>",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<pad>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "<unk>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": true,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
}
|
tokenizer_config.json
CHANGED
@@ -2,49 +2,49 @@
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<s>",
|
5 |
-
"lstrip":
|
6 |
"normalized": false,
|
7 |
-
"rstrip":
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
"content": "<pad>",
|
13 |
-
"lstrip":
|
14 |
"normalized": false,
|
15 |
-
"rstrip":
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
-
"lstrip":
|
22 |
"normalized": false,
|
23 |
-
"rstrip":
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
-
"lstrip":
|
30 |
"normalized": false,
|
31 |
-
"rstrip":
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
"79": {
|
36 |
"content": "<mask>",
|
37 |
-
"lstrip":
|
38 |
-
"normalized":
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
"80": {
|
44 |
"content": "<ctc_blank>",
|
45 |
-
"lstrip":
|
46 |
"normalized": true,
|
47 |
-
"rstrip":
|
48 |
"single_word": false,
|
49 |
"special": false
|
50 |
},
|
@@ -441,13 +441,6 @@
|
|
441 |
"special": false
|
442 |
}
|
443 |
},
|
444 |
-
"additional_special_tokens": [
|
445 |
-
"<s>",
|
446 |
-
"<pad>",
|
447 |
-
"</s>",
|
448 |
-
"<unk>",
|
449 |
-
"<mask>"
|
450 |
-
],
|
451 |
"bos_token": "<s>",
|
452 |
"clean_up_tokenization_spaces": true,
|
453 |
"eos_token": "</s>",
|
@@ -458,6 +451,5 @@
|
|
458 |
"processor_class": "SpeechT5Processor",
|
459 |
"sp_model_kwargs": {},
|
460 |
"tokenizer_class": "SpeechT5Tokenizer",
|
461 |
-
"tokenizer_file": null,
|
462 |
"unk_token": "<unk>"
|
463 |
}
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<s>",
|
5 |
+
"lstrip": true,
|
6 |
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
"content": "<pad>",
|
13 |
+
"lstrip": true,
|
14 |
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
+
"lstrip": true,
|
22 |
"normalized": false,
|
23 |
+
"rstrip": true,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
+
"lstrip": true,
|
30 |
"normalized": false,
|
31 |
+
"rstrip": true,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
"79": {
|
36 |
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
"80": {
|
44 |
"content": "<ctc_blank>",
|
45 |
+
"lstrip": false,
|
46 |
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": false
|
50 |
},
|
|
|
441 |
"special": false
|
442 |
}
|
443 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
444 |
"bos_token": "<s>",
|
445 |
"clean_up_tokenization_spaces": true,
|
446 |
"eos_token": "</s>",
|
|
|
451 |
"processor_class": "SpeechT5Processor",
|
452 |
"sp_model_kwargs": {},
|
453 |
"tokenizer_class": "SpeechT5Tokenizer",
|
|
|
454 |
"unk_token": "<unk>"
|
455 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ad1084162a7f31279684259baad1a0cc84aa14100381a07039bb3d89ed0ff68
|
3 |
size 4664
|