Commit
·
611063a
1
Parent(s):
32b226d
Trained another ~3 epochs
Browse files- config.json +2 -2
- generation_config.json +1 -110
- preprocessor_config.json +0 -0
- pytorch_model.bin +1 -1
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
@@ -44,7 +44,7 @@
|
|
44 |
"scale_embedding": false,
|
45 |
"suppress_tokens": [],
|
46 |
"torch_dtype": "float32",
|
47 |
-
"transformers_version": "4.
|
48 |
"use_cache": true,
|
49 |
"use_weighted_layer_sum": false,
|
50 |
"vocab_size": 51865
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "sadidul012/whisper-small-bengali",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
44 |
"scale_embedding": false,
|
45 |
"suppress_tokens": [],
|
46 |
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.26.1",
|
48 |
"use_cache": true,
|
49 |
"use_weighted_layer_sum": false,
|
50 |
"vocab_size": 51865
|
generation_config.json
CHANGED
@@ -16,113 +16,8 @@
|
|
16 |
50359
|
17 |
]
|
18 |
],
|
19 |
-
"is_multilingual": true,
|
20 |
-
"lang_to_id": {
|
21 |
-
"<|af|>": 50327,
|
22 |
-
"<|am|>": 50334,
|
23 |
-
"<|ar|>": 50272,
|
24 |
-
"<|as|>": 50350,
|
25 |
-
"<|az|>": 50304,
|
26 |
-
"<|ba|>": 50355,
|
27 |
-
"<|be|>": 50330,
|
28 |
-
"<|bg|>": 50292,
|
29 |
-
"<|bn|>": 50302,
|
30 |
-
"<|bo|>": 50347,
|
31 |
-
"<|br|>": 50309,
|
32 |
-
"<|bs|>": 50315,
|
33 |
-
"<|ca|>": 50270,
|
34 |
-
"<|cs|>": 50283,
|
35 |
-
"<|cy|>": 50297,
|
36 |
-
"<|da|>": 50285,
|
37 |
-
"<|de|>": 50261,
|
38 |
-
"<|el|>": 50281,
|
39 |
-
"<|en|>": 50259,
|
40 |
-
"<|es|>": 50262,
|
41 |
-
"<|et|>": 50307,
|
42 |
-
"<|eu|>": 50310,
|
43 |
-
"<|fa|>": 50300,
|
44 |
-
"<|fi|>": 50277,
|
45 |
-
"<|fo|>": 50338,
|
46 |
-
"<|fr|>": 50265,
|
47 |
-
"<|gl|>": 50319,
|
48 |
-
"<|gu|>": 50333,
|
49 |
-
"<|haw|>": 50352,
|
50 |
-
"<|ha|>": 50354,
|
51 |
-
"<|he|>": 50279,
|
52 |
-
"<|hi|>": 50276,
|
53 |
-
"<|hr|>": 50291,
|
54 |
-
"<|ht|>": 50339,
|
55 |
-
"<|hu|>": 50286,
|
56 |
-
"<|hy|>": 50312,
|
57 |
-
"<|id|>": 50275,
|
58 |
-
"<|is|>": 50311,
|
59 |
-
"<|it|>": 50274,
|
60 |
-
"<|ja|>": 50266,
|
61 |
-
"<|jw|>": 50356,
|
62 |
-
"<|ka|>": 50329,
|
63 |
-
"<|kk|>": 50316,
|
64 |
-
"<|km|>": 50323,
|
65 |
-
"<|kn|>": 50306,
|
66 |
-
"<|ko|>": 50264,
|
67 |
-
"<|la|>": 50294,
|
68 |
-
"<|lb|>": 50345,
|
69 |
-
"<|ln|>": 50353,
|
70 |
-
"<|lo|>": 50336,
|
71 |
-
"<|lt|>": 50293,
|
72 |
-
"<|lv|>": 50301,
|
73 |
-
"<|mg|>": 50349,
|
74 |
-
"<|mi|>": 50295,
|
75 |
-
"<|mk|>": 50308,
|
76 |
-
"<|ml|>": 50296,
|
77 |
-
"<|mn|>": 50314,
|
78 |
-
"<|mr|>": 50320,
|
79 |
-
"<|ms|>": 50282,
|
80 |
-
"<|mt|>": 50343,
|
81 |
-
"<|my|>": 50346,
|
82 |
-
"<|ne|>": 50313,
|
83 |
-
"<|nl|>": 50271,
|
84 |
-
"<|nn|>": 50342,
|
85 |
-
"<|no|>": 50288,
|
86 |
-
"<|oc|>": 50328,
|
87 |
-
"<|pa|>": 50321,
|
88 |
-
"<|pl|>": 50269,
|
89 |
-
"<|ps|>": 50340,
|
90 |
-
"<|pt|>": 50267,
|
91 |
-
"<|ro|>": 50284,
|
92 |
-
"<|ru|>": 50263,
|
93 |
-
"<|sa|>": 50344,
|
94 |
-
"<|sd|>": 50332,
|
95 |
-
"<|si|>": 50322,
|
96 |
-
"<|sk|>": 50298,
|
97 |
-
"<|sl|>": 50305,
|
98 |
-
"<|sn|>": 50324,
|
99 |
-
"<|so|>": 50326,
|
100 |
-
"<|sq|>": 50317,
|
101 |
-
"<|sr|>": 50303,
|
102 |
-
"<|su|>": 50357,
|
103 |
-
"<|sv|>": 50273,
|
104 |
-
"<|sw|>": 50318,
|
105 |
-
"<|ta|>": 50287,
|
106 |
-
"<|te|>": 50299,
|
107 |
-
"<|tg|>": 50331,
|
108 |
-
"<|th|>": 50289,
|
109 |
-
"<|tk|>": 50341,
|
110 |
-
"<|tl|>": 50348,
|
111 |
-
"<|tr|>": 50268,
|
112 |
-
"<|tt|>": 50351,
|
113 |
-
"<|uk|>": 50280,
|
114 |
-
"<|ur|>": 50290,
|
115 |
-
"<|uz|>": 50337,
|
116 |
-
"<|vi|>": 50278,
|
117 |
-
"<|yi|>": 50335,
|
118 |
-
"<|yo|>": 50325,
|
119 |
-
"<|zh|>": 50260
|
120 |
-
},
|
121 |
-
"max_initial_timestamp_index": 1,
|
122 |
"max_length": 448,
|
123 |
-
"no_timestamps_token_id": 50363,
|
124 |
"pad_token_id": 50257,
|
125 |
-
"return_timestamps": false,
|
126 |
"suppress_tokens": [
|
127 |
1,
|
128 |
2,
|
@@ -213,9 +108,5 @@
|
|
213 |
50361,
|
214 |
50362
|
215 |
],
|
216 |
-
"
|
217 |
-
"transcribe": 50359,
|
218 |
-
"translate": 50358
|
219 |
-
},
|
220 |
-
"transformers_version": "4.29.1"
|
221 |
}
|
|
|
16 |
50359
|
17 |
]
|
18 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"max_length": 448,
|
|
|
20 |
"pad_token_id": 50257,
|
|
|
21 |
"suppress_tokens": [
|
22 |
1,
|
23 |
2,
|
|
|
108 |
50361,
|
109 |
50362
|
110 |
],
|
111 |
+
"transformers_version": "4.26.1"
|
|
|
|
|
|
|
|
|
112 |
}
|
preprocessor_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49c140e239701f2846fe9c3f94773dea83884bdf2285f65da90ed117dc250bb6
|
3 |
size 967102601
|
tokenizer_config.json
CHANGED
@@ -20,9 +20,11 @@
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 1024,
|
|
|
23 |
"pad_token": null,
|
24 |
"processor_class": "WhisperProcessor",
|
25 |
"return_attention_mask": false,
|
|
|
26 |
"tokenizer_class": "WhisperTokenizer",
|
27 |
"unk_token": {
|
28 |
"__type": "AddedToken",
|
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 1024,
|
23 |
+
"name_or_path": "sadidul012/whisper-small-bengali",
|
24 |
"pad_token": null,
|
25 |
"processor_class": "WhisperProcessor",
|
26 |
"return_attention_mask": false,
|
27 |
+
"special_tokens_map_file": "/home/sadid/.cache/huggingface/hub/models--sadidul012--whisper-small-bengali/snapshots/32b226d60673f53aeb16d5baf3f5c41757f8b223/special_tokens_map.json",
|
28 |
"tokenizer_class": "WhisperTokenizer",
|
29 |
"unk_token": {
|
30 |
"__type": "AddedToken",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b20e4044759584f3561c8944278374f32fb9975090466ed55bcda2ea2dcdc6e0
|
3 |
+
size 3643
|