Hugging Face's logo

eemberda
/
phcodeswitch-ceb-dvo

Automatic Speech Recognition
Safetensors
Tagalog
Cebuano
English
whisper
cebuano
filipino
tagalog
cebuano-asr
bisaya
bisaya-asr
code-switching
Model card Files
xet
 Community
eemberda commited on
Commit
9540ff1
·
verified ·
1 Parent(s): 5488437

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. best_model_summary.json +6 -0
  2. config.json +150 -59
  3. generation_config.json +286 -270
  4. model.safetensors +2 -2
  5. preprocessor_config.json +14 -0
  6. processor_config.json +17 -17
  7. tokenizer.json +0 -42
  8. tokenizer_config.json +128 -127
  9. training_args.bin +2 -2
  10. training_config.json +21 -21
best_model_summary.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "best_wer": 20.86,
3
+ "best_step": "1200",
4
+ "total_steps": 1800,
5
+ "best_model_checkpoint": "asr_model_output\\checkpoint-1200"
6
+ }
config.json CHANGED
@@ -1,59 +1,150 @@
1
- {
2
- "activation_dropout": 0.0,
3
- "activation_function": "gelu",
4
- "apply_spec_augment": false,
5
- "architectures": [
6
- "WhisperForConditionalGeneration"
7
- ],
8
- "attention_dropout": 0.0,
9
- "bos_token_id": 50257,
10
- "classifier_proj_size": 256,
11
- "d_model": 384,
12
- "decoder_attention_heads": 6,
13
- "decoder_ffn_dim": 1536,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 4,
16
- "decoder_start_token_id": 50258,
17
- "dropout": 0.0,
18
- "dtype": "float32",
19
- "encoder_attention_heads": 6,
20
- "encoder_ffn_dim": 1536,
21
- "encoder_layerdrop": 0.0,
22
- "encoder_layers": 4,
23
- "eos_token_id": 50257,
24
- "forced_decoder_ids": [
25
- [
26
- 1,
27
- 50259
28
- ],
29
- [
30
- 2,
31
- 50359
32
- ],
33
- [
34
- 3,
35
- 50363
36
- ]
37
- ],
38
- "init_std": 0.02,
39
- "is_encoder_decoder": true,
40
- "mask_feature_length": 10,
41
- "mask_feature_min_masks": 0,
42
- "mask_feature_prob": 0.0,
43
- "mask_time_length": 10,
44
- "mask_time_min_masks": 2,
45
- "mask_time_prob": 0.05,
46
- "max_source_positions": 1500,
47
- "max_target_positions": 448,
48
- "median_filter_width": 7,
49
- "model_type": "whisper",
50
- "num_hidden_layers": 4,
51
- "num_mel_bins": 80,
52
- "pad_token_id": 50257,
53
- "scale_embedding": false,
54
- "tie_word_embeddings": true,
55
- "transformers_version": "5.0.0",
56
- "use_cache": false,
57
- "use_weighted_layer_sum": false,
58
- "vocab_size": 51865
59
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "classifier_proj_size": 256,
15
+ "d_model": 768,
16
+ "decoder_attention_heads": 12,
17
+ "decoder_ffn_dim": 3072,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 50258,
21
+ "dropout": 0.0,
22
+ "dtype": "float32",
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_source_positions": 1500,
51
+ "max_target_positions": 448,
52
+ "median_filter_width": 7,
53
+ "model_type": "whisper",
54
+ "num_mel_bins": 80,
55
+ "pad_token_id": 50257,
56
+ "scale_embedding": false,
57
+ "suppress_tokens": [
58
+ 1,
59
+ 2,
60
+ 7,
61
+ 8,
62
+ 9,
63
+ 10,
64
+ 14,
65
+ 25,
66
+ 26,
67
+ 27,
68
+ 28,
69
+ 29,
70
+ 31,
71
+ 58,
72
+ 59,
73
+ 60,
74
+ 61,
75
+ 62,
76
+ 63,
77
+ 90,
78
+ 91,
79
+ 92,
80
+ 93,
81
+ 359,
82
+ 503,
83
+ 522,
84
+ 542,
85
+ 873,
86
+ 893,
87
+ 902,
88
+ 918,
89
+ 922,
90
+ 931,
91
+ 1350,
92
+ 1853,
93
+ 1982,
94
+ 2460,
95
+ 2627,
96
+ 3246,
97
+ 3253,
98
+ 3268,
99
+ 3536,
100
+ 3846,
101
+ 3961,
102
+ 4183,
103
+ 4667,
104
+ 6585,
105
+ 6647,
106
+ 7273,
107
+ 9061,
108
+ 9383,
109
+ 10428,
110
+ 10929,
111
+ 11938,
112
+ 12033,
113
+ 12331,
114
+ 12562,
115
+ 13793,
116
+ 14157,
117
+ 14635,
118
+ 15265,
119
+ 15618,
120
+ 16553,
121
+ 16604,
122
+ 18362,
123
+ 18956,
124
+ 20075,
125
+ 21675,
126
+ 22520,
127
+ 26130,
128
+ 26161,
129
+ 26435,
130
+ 28279,
131
+ 29464,
132
+ 31650,
133
+ 32302,
134
+ 32470,
135
+ 36865,
136
+ 42863,
137
+ 47425,
138
+ 49870,
139
+ 50254,
140
+ 50258,
141
+ 50360,
142
+ 50361,
143
+ 50362
144
+ ],
145
+ "tie_word_embeddings": true,
146
+ "transformers_version": "5.14.1",
147
+ "use_cache": false,
148
+ "use_weighted_layer_sum": false,
149
+ "vocab_size": 51865
150
+ }
generation_config.json CHANGED
@@ -1,270 +1,286 @@
1
- {
2
- "alignment_heads": [
3
- [
4
- 2,
5
- 2
6
- ],
7
- [
8
- 3,
9
- 0
10
- ],
11
- [
12
- 3,
13
- 2
14
- ],
15
- [
16
- 3,
17
- 3
18
- ],
19
- [
20
- 3,
21
- 4
22
- ],
23
- [
24
- 3,
25
- 5
26
- ]
27
- ],
28
- "assistant_confidence_threshold": 0.4,
29
- "assistant_lookbehind": 10,
30
- "begin_suppress_tokens": [
31
- 220,
32
- 50257
33
- ],
34
- "bos_token_id": 50257,
35
- "decoder_start_token_id": 50258,
36
- "diversity_penalty": 0.0,
37
- "do_sample": false,
38
- "early_stopping": false,
39
- "encoder_no_repeat_ngram_size": 0,
40
- "encoder_repetition_penalty": 1.0,
41
- "eos_token_id": [
42
- 50257
43
- ],
44
- "epsilon_cutoff": 0.0,
45
- "eta_cutoff": 0.0,
46
- "forced_decoder_ids": null,
47
- "is_multilingual": true,
48
- "lang_to_id": {
49
- "<|af|>": 50327,
50
- "<|am|>": 50334,
51
- "<|ar|>": 50272,
52
- "<|as|>": 50350,
53
- "<|az|>": 50304,
54
- "<|ba|>": 50355,
55
- "<|be|>": 50330,
56
- "<|bg|>": 50292,
57
- "<|bn|>": 50302,
58
- "<|bo|>": 50347,
59
- "<|br|>": 50309,
60
- "<|bs|>": 50315,
61
- "<|ca|>": 50270,
62
- "<|cs|>": 50283,
63
- "<|cy|>": 50297,
64
- "<|da|>": 50285,
65
- "<|de|>": 50261,
66
- "<|el|>": 50281,
67
- "<|en|>": 50259,
68
- "<|es|>": 50262,
69
- "<|et|>": 50307,
70
- "<|eu|>": 50310,
71
- "<|fa|>": 50300,
72
- "<|fi|>": 50277,
73
- "<|fo|>": 50338,
74
- "<|fr|>": 50265,
75
- "<|gl|>": 50319,
76
- "<|gu|>": 50333,
77
- "<|haw|>": 50352,
78
- "<|ha|>": 50354,
79
- "<|he|>": 50279,
80
- "<|hi|>": 50276,
81
- "<|hr|>": 50291,
82
- "<|ht|>": 50339,
83
- "<|hu|>": 50286,
84
- "<|hy|>": 50312,
85
- "<|id|>": 50275,
86
- "<|is|>": 50311,
87
- "<|it|>": 50274,
88
- "<|ja|>": 50266,
89
- "<|jw|>": 50356,
90
- "<|ka|>": 50329,
91
- "<|kk|>": 50316,
92
- "<|km|>": 50323,
93
- "<|kn|>": 50306,
94
- "<|ko|>": 50264,
95
- "<|la|>": 50294,
96
- "<|lb|>": 50345,
97
- "<|ln|>": 50353,
98
- "<|lo|>": 50336,
99
- "<|lt|>": 50293,
100
- "<|lv|>": 50301,
101
- "<|mg|>": 50349,
102
- "<|mi|>": 50295,
103
- "<|mk|>": 50308,
104
- "<|ml|>": 50296,
105
- "<|mn|>": 50314,
106
- "<|mr|>": 50320,
107
- "<|ms|>": 50282,
108
- "<|mt|>": 50343,
109
- "<|my|>": 50346,
110
- "<|ne|>": 50313,
111
- "<|nl|>": 50271,
112
- "<|nn|>": 50342,
113
- "<|no|>": 50288,
114
- "<|oc|>": 50328,
115
- "<|pa|>": 50321,
116
- "<|pl|>": 50269,
117
- "<|ps|>": 50340,
118
- "<|pt|>": 50267,
119
- "<|ro|>": 50284,
120
- "<|ru|>": 50263,
121
- "<|sa|>": 50344,
122
- "<|sd|>": 50332,
123
- "<|si|>": 50322,
124
- "<|sk|>": 50298,
125
- "<|sl|>": 50305,
126
- "<|sn|>": 50324,
127
- "<|so|>": 50326,
128
- "<|sq|>": 50317,
129
- "<|sr|>": 50303,
130
- "<|su|>": 50357,
131
- "<|sv|>": 50273,
132
- "<|sw|>": 50318,
133
- "<|ta|>": 50287,
134
- "<|te|>": 50299,
135
- "<|tg|>": 50331,
136
- "<|th|>": 50289,
137
- "<|tk|>": 50341,
138
- "<|tl|>": 50348,
139
- "<|tr|>": 50268,
140
- "<|tt|>": 50351,
141
- "<|uk|>": 50280,
142
- "<|ur|>": 50290,
143
- "<|uz|>": 50337,
144
- "<|vi|>": 50278,
145
- "<|yi|>": 50335,
146
- "<|yo|>": 50325,
147
- "<|zh|>": 50260
148
- },
149
- "language": "tagalog",
150
- "length_penalty": 1.0,
151
- "max_initial_timestamp_index": 50,
152
- "max_length": 448,
153
- "min_length": 0,
154
- "no_repeat_ngram_size": 0,
155
- "no_timestamps_token_id": 50363,
156
- "num_assistant_tokens": 20,
157
- "num_assistant_tokens_schedule": "constant",
158
- "num_beam_groups": 1,
159
- "num_beams": 1,
160
- "num_return_sequences": 1,
161
- "output_scores": false,
162
- "pad_token_id": 50257,
163
- "prev_sot_token_id": 50361,
164
- "remove_invalid_values": false,
165
- "repetition_penalty": 1.0,
166
- "return_dict_in_generate": false,
167
- "return_timestamps": false,
168
- "suppress_tokens": [
169
- 1,
170
- 2,
171
- 7,
172
- 8,
173
- 9,
174
- 10,
175
- 14,
176
- 25,
177
- 26,
178
- 27,
179
- 28,
180
- 29,
181
- 31,
182
- 58,
183
- 59,
184
- 60,
185
- 61,
186
- 62,
187
- 63,
188
- 90,
189
- 91,
190
- 92,
191
- 93,
192
- 359,
193
- 503,
194
- 522,
195
- 542,
196
- 873,
197
- 893,
198
- 902,
199
- 918,
200
- 922,
201
- 931,
202
- 1350,
203
- 1853,
204
- 1982,
205
- 2460,
206
- 2627,
207
- 3246,
208
- 3253,
209
- 3268,
210
- 3536,
211
- 3846,
212
- 3961,
213
- 4183,
214
- 4667,
215
- 6585,
216
- 6647,
217
- 7273,
218
- 9061,
219
- 9383,
220
- 10428,
221
- 10929,
222
- 11938,
223
- 12033,
224
- 12331,
225
- 12562,
226
- 13793,
227
- 14157,
228
- 14635,
229
- 15265,
230
- 15618,
231
- 16553,
232
- 16604,
233
- 18362,
234
- 18956,
235
- 20075,
236
- 21675,
237
- 22520,
238
- 26130,
239
- 26161,
240
- 26435,
241
- 28279,
242
- 29464,
243
- 31650,
244
- 32302,
245
- 32470,
246
- 36865,
247
- 42863,
248
- 47425,
249
- 49870,
250
- 50254,
251
- 50258,
252
- 50358,
253
- 50359,
254
- 50360,
255
- 50361,
256
- 50362
257
- ],
258
- "target_lookbehind": 10,
259
- "task": "transcribe",
260
- "task_to_id": {
261
- "transcribe": 50359,
262
- "translate": 50358
263
- },
264
- "temperature": 1.0,
265
- "top_k": 50,
266
- "top_p": 1.0,
267
- "transformers_version": "5.0.0",
268
- "typical_p": 1.0,
269
- "use_cache": true
270
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "assistant_confidence_threshold": 0.4,
45
+ "assistant_lookbehind": 10,
46
+ "begin_suppress_tokens": [
47
+ 220,
48
+ 50257
49
+ ],
50
+ "bos_token_id": 50257,
51
+ "decoder_start_token_id": 50258,
52
+ "diversity_penalty": 0.0,
53
+ "do_sample": false,
54
+ "early_stopping": false,
55
+ "encoder_no_repeat_ngram_size": 0,
56
+ "encoder_repetition_penalty": 1.0,
57
+ "eos_token_id": [
58
+ 50257
59
+ ],
60
+ "epsilon_cutoff": 0.0,
61
+ "eta_cutoff": 0.0,
62
+ "forced_decoder_ids": null,
63
+ "is_multilingual": true,
64
+ "lang_to_id": {
65
+ "<|af|>": 50327,
66
+ "<|am|>": 50334,
67
+ "<|ar|>": 50272,
68
+ "<|as|>": 50350,
69
+ "<|az|>": 50304,
70
+ "<|ba|>": 50355,
71
+ "<|be|>": 50330,
72
+ "<|bg|>": 50292,
73
+ "<|bn|>": 50302,
74
+ "<|bo|>": 50347,
75
+ "<|br|>": 50309,
76
+ "<|bs|>": 50315,
77
+ "<|ca|>": 50270,
78
+ "<|cs|>": 50283,
79
+ "<|cy|>": 50297,
80
+ "<|da|>": 50285,
81
+ "<|de|>": 50261,
82
+ "<|el|>": 50281,
83
+ "<|en|>": 50259,
84
+ "<|es|>": 50262,
85
+ "<|et|>": 50307,
86
+ "<|eu|>": 50310,
87
+ "<|fa|>": 50300,
88
+ "<|fi|>": 50277,
89
+ "<|fo|>": 50338,
90
+ "<|fr|>": 50265,
91
+ "<|gl|>": 50319,
92
+ "<|gu|>": 50333,
93
+ "<|haw|>": 50352,
94
+ "<|ha|>": 50354,
95
+ "<|he|>": 50279,
96
+ "<|hi|>": 50276,
97
+ "<|hr|>": 50291,
98
+ "<|ht|>": 50339,
99
+ "<|hu|>": 50286,
100
+ "<|hy|>": 50312,
101
+ "<|id|>": 50275,
102
+ "<|is|>": 50311,
103
+ "<|it|>": 50274,
104
+ "<|ja|>": 50266,
105
+ "<|jw|>": 50356,
106
+ "<|ka|>": 50329,
107
+ "<|kk|>": 50316,
108
+ "<|km|>": 50323,
109
+ "<|kn|>": 50306,
110
+ "<|ko|>": 50264,
111
+ "<|la|>": 50294,
112
+ "<|lb|>": 50345,
113
+ "<|ln|>": 50353,
114
+ "<|lo|>": 50336,
115
+ "<|lt|>": 50293,
116
+ "<|lv|>": 50301,
117
+ "<|mg|>": 50349,
118
+ "<|mi|>": 50295,
119
+ "<|mk|>": 50308,
120
+ "<|ml|>": 50296,
121
+ "<|mn|>": 50314,
122
+ "<|mr|>": 50320,
123
+ "<|ms|>": 50282,
124
+ "<|mt|>": 50343,
125
+ "<|my|>": 50346,
126
+ "<|ne|>": 50313,
127
+ "<|nl|>": 50271,
128
+ "<|nn|>": 50342,
129
+ "<|no|>": 50288,
130
+ "<|oc|>": 50328,
131
+ "<|pa|>": 50321,
132
+ "<|pl|>": 50269,
133
+ "<|ps|>": 50340,
134
+ "<|pt|>": 50267,
135
+ "<|ro|>": 50284,
136
+ "<|ru|>": 50263,
137
+ "<|sa|>": 50344,
138
+ "<|sd|>": 50332,
139
+ "<|si|>": 50322,
140
+ "<|sk|>": 50298,
141
+ "<|sl|>": 50305,
142
+ "<|sn|>": 50324,
143
+ "<|so|>": 50326,
144
+ "<|sq|>": 50317,
145
+ "<|sr|>": 50303,
146
+ "<|su|>": 50357,
147
+ "<|sv|>": 50273,
148
+ "<|sw|>": 50318,
149
+ "<|ta|>": 50287,
150
+ "<|te|>": 50299,
151
+ "<|tg|>": 50331,
152
+ "<|th|>": 50289,
153
+ "<|tk|>": 50341,
154
+ "<|tl|>": 50348,
155
+ "<|tr|>": 50268,
156
+ "<|tt|>": 50351,
157
+ "<|uk|>": 50280,
158
+ "<|ur|>": 50290,
159
+ "<|uz|>": 50337,
160
+ "<|vi|>": 50278,
161
+ "<|yi|>": 50335,
162
+ "<|yo|>": 50325,
163
+ "<|zh|>": 50260
164
+ },
165
+ "language": "tagalog",
166
+ "length_penalty": 1.0,
167
+ "max_initial_timestamp_index": 50,
168
+ "max_length": 448,
169
+ "min_length": 0,
170
+ "no_repeat_ngram_size": 0,
171
+ "no_timestamps_token_id": 50363,
172
+ "num_assistant_tokens": 20,
173
+ "num_assistant_tokens_schedule": "constant",
174
+ "num_beam_groups": 1,
175
+ "num_beams": 1,
176
+ "num_return_sequences": 1,
177
+ "output_scores": false,
178
+ "pad_token_id": 50257,
179
+ "prev_sot_token_id": 50361,
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict_in_generate": false,
183
+ "return_timestamps": false,
184
+ "suppress_tokens": [
185
+ 1,
186
+ 2,
187
+ 7,
188
+ 8,
189
+ 9,
190
+ 10,
191
+ 14,
192
+ 25,
193
+ 26,
194
+ 27,
195
+ 28,
196
+ 29,
197
+ 31,
198
+ 58,
199
+ 59,
200
+ 60,
201
+ 61,
202
+ 62,
203
+ 63,
204
+ 90,
205
+ 91,
206
+ 92,
207
+ 93,
208
+ 359,
209
+ 503,
210
+ 522,
211
+ 542,
212
+ 873,
213
+ 893,
214
+ 902,
215
+ 918,
216
+ 922,
217
+ 931,
218
+ 1350,
219
+ 1853,
220
+ 1982,
221
+ 2460,
222
+ 2627,
223
+ 3246,
224
+ 3253,
225
+ 3268,
226
+ 3536,
227
+ 3846,
228
+ 3961,
229
+ 4183,
230
+ 4667,
231
+ 6585,
232
+ 6647,
233
+ 7273,
234
+ 9061,
235
+ 9383,
236
+ 10428,
237
+ 10929,
238
+ 11938,
239
+ 12033,
240
+ 12331,
241
+ 12562,
242
+ 13793,
243
+ 14157,
244
+ 14635,
245
+ 15265,
246
+ 15618,
247
+ 16553,
248
+ 16604,
249
+ 18362,
250
+ 18956,
251
+ 20075,
252
+ 21675,
253
+ 22520,
254
+ 26130,
255
+ 26161,
256
+ 26435,
257
+ 28279,
258
+ 29464,
259
+ 31650,
260
+ 32302,
261
+ 32470,
262
+ 36865,
263
+ 42863,
264
+ 47425,
265
+ 49870,
266
+ 50254,
267
+ 50258,
268
+ 50358,
269
+ 50359,
270
+ 50360,
271
+ 50361,
272
+ 50362
273
+ ],
274
+ "target_lookbehind": 10,
275
+ "task": "transcribe",
276
+ "task_to_id": {
277
+ "transcribe": 50359,
278
+ "translate": 50358
279
+ },
280
+ "temperature": 1.0,
281
+ "top_k": 50,
282
+ "top_p": 1.0,
283
+ "transformers_version": "5.14.1",
284
+ "typical_p": 1.0,
285
+ "use_cache": true
286
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9aabb801448f7153f2b89fd142e2e45d2902ecded5380a37e98353287d298898
3
- size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2bc3696905b5fbddce5687b7bcfec15d841d8b6530a9602a2e90d8249559d7
3
+ size 966995080
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
processor_config.json CHANGED
@@ -1,17 +1,17 @@
1
- {
2
- "feature_extractor": {
3
- "chunk_length": 30,
4
- "dither": 0.0,
5
- "feature_extractor_type": "WhisperFeatureExtractor",
6
- "feature_size": 80,
7
- "hop_length": 160,
8
- "n_fft": 400,
9
- "n_samples": 480000,
10
- "nb_max_frames": 3000,
11
- "padding_side": "right",
12
- "padding_value": 0.0,
13
- "return_attention_mask": false,
14
- "sampling_rate": 16000
15
- },
16
- "processor_class": "WhisperProcessor"
17
- }
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "WhisperProcessor"
17
+ }
tokenizer.json CHANGED
@@ -14492,18 +14492,6 @@
14492
  "type_id": 0
14493
  }
14494
  },
14495
- {
14496
- "SpecialToken": {
14497
- "id": "<|tl|>",
14498
- "type_id": 0
14499
- }
14500
- },
14501
- {
14502
- "SpecialToken": {
14503
- "id": "<|transcribe|>",
14504
- "type_id": 0
14505
- }
14506
- },
14507
  {
14508
  "SpecialToken": {
14509
  "id": "<|notimestamps|>",
@@ -14530,18 +14518,6 @@
14530
  "type_id": 0
14531
  }
14532
  },
14533
- {
14534
- "SpecialToken": {
14535
- "id": "<|tl|>",
14536
- "type_id": 0
14537
- }
14538
- },
14539
- {
14540
- "SpecialToken": {
14541
- "id": "<|transcribe|>",
14542
- "type_id": 0
14543
- }
14544
- },
14545
  {
14546
  "SpecialToken": {
14547
  "id": "<|notimestamps|>",
@@ -14594,24 +14570,6 @@
14594
  "tokens": [
14595
  "<|startoftranscript|>"
14596
  ]
14597
- },
14598
- "<|tl|>": {
14599
- "id": "<|tl|>",
14600
- "ids": [
14601
- 50348
14602
- ],
14603
- "tokens": [
14604
- "<|tl|>"
14605
- ]
14606
- },
14607
- "<|transcribe|>": {
14608
- "id": "<|transcribe|>",
14609
- "ids": [
14610
- 50359
14611
- ],
14612
- "tokens": [
14613
- "<|transcribe|>"
14614
- ]
14615
  }
14616
  }
14617
  },
 
14492
  "type_id": 0
14493
  }
14494
  },
 
 
 
 
 
 
 
 
 
 
 
 
14495
  {
14496
  "SpecialToken": {
14497
  "id": "<|notimestamps|>",
 
14518
  "type_id": 0
14519
  }
14520
  },
 
 
 
 
 
 
 
 
 
 
 
 
14521
  {
14522
  "SpecialToken": {
14523
  "id": "<|notimestamps|>",
 
14570
  "tokens": [
14571
  "<|startoftranscript|>"
14572
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14573
  }
14574
  }
14575
  },
tokenizer_config.json CHANGED
@@ -1,127 +1,128 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": "<|endoftext|>",
5
- "clean_up_tokenization_spaces": true,
6
- "eos_token": "<|endoftext|>",
7
- "errors": "replace",
8
- "extra_special_tokens": [
9
- "<|endoftext|>",
10
- "<|startoftranscript|>",
11
- "<|en|>",
12
- "<|zh|>",
13
- "<|de|>",
14
- "<|es|>",
15
- "<|ru|>",
16
- "<|ko|>",
17
- "<|fr|>",
18
- "<|ja|>",
19
- "<|pt|>",
20
- "<|tr|>",
21
- "<|pl|>",
22
- "<|ca|>",
23
- "<|nl|>",
24
- "<|ar|>",
25
- "<|sv|>",
26
- "<|it|>",
27
- "<|id|>",
28
- "<|hi|>",
29
- "<|fi|>",
30
- "<|vi|>",
31
- "<|he|>",
32
- "<|uk|>",
33
- "<|el|>",
34
- "<|ms|>",
35
- "<|cs|>",
36
- "<|ro|>",
37
- "<|da|>",
38
- "<|hu|>",
39
- "<|ta|>",
40
- "<|no|>",
41
- "<|th|>",
42
- "<|ur|>",
43
- "<|hr|>",
44
- "<|bg|>",
45
- "<|lt|>",
46
- "<|la|>",
47
- "<|mi|>",
48
- "<|ml|>",
49
- "<|cy|>",
50
- "<|sk|>",
51
- "<|te|>",
52
- "<|fa|>",
53
- "<|lv|>",
54
- "<|bn|>",
55
- "<|sr|>",
56
- "<|az|>",
57
- "<|sl|>",
58
- "<|kn|>",
59
- "<|et|>",
60
- "<|mk|>",
61
- "<|br|>",
62
- "<|eu|>",
63
- "<|is|>",
64
- "<|hy|>",
65
- "<|ne|>",
66
- "<|mn|>",
67
- "<|bs|>",
68
- "<|kk|>",
69
- "<|sq|>",
70
- "<|sw|>",
71
- "<|gl|>",
72
- "<|mr|>",
73
- "<|pa|>",
74
- "<|si|>",
75
- "<|km|>",
76
- "<|sn|>",
77
- "<|yo|>",
78
- "<|so|>",
79
- "<|af|>",
80
- "<|oc|>",
81
- "<|ka|>",
82
- "<|be|>",
83
- "<|tg|>",
84
- "<|sd|>",
85
- "<|gu|>",
86
- "<|am|>",
87
- "<|yi|>",
88
- "<|lo|>",
89
- "<|uz|>",
90
- "<|fo|>",
91
- "<|ht|>",
92
- "<|ps|>",
93
- "<|tk|>",
94
- "<|nn|>",
95
- "<|mt|>",
96
- "<|sa|>",
97
- "<|lb|>",
98
- "<|my|>",
99
- "<|bo|>",
100
- "<|tl|>",
101
- "<|mg|>",
102
- "<|as|>",
103
- "<|tt|>",
104
- "<|haw|>",
105
- "<|ln|>",
106
- "<|ha|>",
107
- "<|ba|>",
108
- "<|jw|>",
109
- "<|su|>",
110
- "<|translate|>",
111
- "<|transcribe|>",
112
- "<|startoflm|>",
113
- "<|startofprev|>",
114
- "<|nocaptions|>",
115
- "<|notimestamps|>"
116
- ],
117
- "is_local": false,
118
- "language": "tagalog",
119
- "model_max_length": 1024,
120
- "pad_token": "<|endoftext|>",
121
- "predict_timestamps": false,
122
- "processor_class": "WhisperProcessor",
123
- "return_attention_mask": false,
124
- "task": "transcribe",
125
- "tokenizer_class": "WhisperTokenizer",
126
- "unk_token": "<|endoftext|>"
127
- }
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|startoftranscript|>",
11
+ "<|en|>",
12
+ "<|zh|>",
13
+ "<|de|>",
14
+ "<|es|>",
15
+ "<|ru|>",
16
+ "<|ko|>",
17
+ "<|fr|>",
18
+ "<|ja|>",
19
+ "<|pt|>",
20
+ "<|tr|>",
21
+ "<|pl|>",
22
+ "<|ca|>",
23
+ "<|nl|>",
24
+ "<|ar|>",
25
+ "<|sv|>",
26
+ "<|it|>",
27
+ "<|id|>",
28
+ "<|hi|>",
29
+ "<|fi|>",
30
+ "<|vi|>",
31
+ "<|he|>",
32
+ "<|uk|>",
33
+ "<|el|>",
34
+ "<|ms|>",
35
+ "<|cs|>",
36
+ "<|ro|>",
37
+ "<|da|>",
38
+ "<|hu|>",
39
+ "<|ta|>",
40
+ "<|no|>",
41
+ "<|th|>",
42
+ "<|ur|>",
43
+ "<|hr|>",
44
+ "<|bg|>",
45
+ "<|lt|>",
46
+ "<|la|>",
47
+ "<|mi|>",
48
+ "<|ml|>",
49
+ "<|cy|>",
50
+ "<|sk|>",
51
+ "<|te|>",
52
+ "<|fa|>",
53
+ "<|lv|>",
54
+ "<|bn|>",
55
+ "<|sr|>",
56
+ "<|az|>",
57
+ "<|sl|>",
58
+ "<|kn|>",
59
+ "<|et|>",
60
+ "<|mk|>",
61
+ "<|br|>",
62
+ "<|eu|>",
63
+ "<|is|>",
64
+ "<|hy|>",
65
+ "<|ne|>",
66
+ "<|mn|>",
67
+ "<|bs|>",
68
+ "<|kk|>",
69
+ "<|sq|>",
70
+ "<|sw|>",
71
+ "<|gl|>",
72
+ "<|mr|>",
73
+ "<|pa|>",
74
+ "<|si|>",
75
+ "<|km|>",
76
+ "<|sn|>",
77
+ "<|yo|>",
78
+ "<|so|>",
79
+ "<|af|>",
80
+ "<|oc|>",
81
+ "<|ka|>",
82
+ "<|be|>",
83
+ "<|tg|>",
84
+ "<|sd|>",
85
+ "<|gu|>",
86
+ "<|am|>",
87
+ "<|yi|>",
88
+ "<|lo|>",
89
+ "<|uz|>",
90
+ "<|fo|>",
91
+ "<|ht|>",
92
+ "<|ps|>",
93
+ "<|tk|>",
94
+ "<|nn|>",
95
+ "<|mt|>",
96
+ "<|sa|>",
97
+ "<|lb|>",
98
+ "<|my|>",
99
+ "<|bo|>",
100
+ "<|tl|>",
101
+ "<|mg|>",
102
+ "<|as|>",
103
+ "<|tt|>",
104
+ "<|haw|>",
105
+ "<|ln|>",
106
+ "<|ha|>",
107
+ "<|ba|>",
108
+ "<|jw|>",
109
+ "<|su|>",
110
+ "<|translate|>",
111
+ "<|transcribe|>",
112
+ "<|startoflm|>",
113
+ "<|startofprev|>",
114
+ "<|nocaptions|>",
115
+ "<|notimestamps|>"
116
+ ],
117
+ "is_local": false,
118
+ "language": null,
119
+ "local_files_only": false,
120
+ "model_max_length": 1024,
121
+ "pad_token": "<|endoftext|>",
122
+ "predict_timestamps": false,
123
+ "processor_class": "WhisperProcessor",
124
+ "return_attention_mask": false,
125
+ "task": null,
126
+ "tokenizer_class": "WhisperTokenizer",
127
+ "unk_token": "<|endoftext|>"
128
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbb3b15f5170eb32da345ec00dd5511ed0f880e9638e230020b62fa95e12ccf5
3
- size 5329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf574318374150740a43f375b3cfea2a0d5e9ff0510b2096d3c4047d089446c
3
+ size 4920
training_config.json CHANGED
@@ -1,22 +1,22 @@
1
- {
2
- "audio_dir": "audio_data",
3
- "transcript_file": "audio_data/transcripts.txt",
4
- "metadata_file": "audio_data/metadata.json",
5
- "output_dir": "asr_model_output",
6
- "model_save_path": "asr_model_final",
7
- "base_model": "openai/whisper-tiny",
8
- "language": "tagalog",
9
- "task": "transcribe",
10
- "test_split_ratio": 0.15,
11
- "max_input_length_s": 30.0,
12
- "batch_size": 8,
13
- "grad_accum_steps": 2,
14
- "learning_rate": 1e-05,
15
- "warmup_steps": 100,
16
- "max_steps": 2000,
17
- "eval_steps": 200,
18
- "save_steps": 200,
19
- "fp16": true,
20
- "generation_max_length": 225,
21
- "num_beams": 5
22
  }
 
1
+ {
2
+ "audio_dir": "audio_data",
3
+ "transcript_file": "audio_data/transcripts.txt",
4
+ "metadata_file": "audio_data/metadata.json",
5
+ "output_dir": "asr_model_output",
6
+ "model_save_path": "asr_model_final",
7
+ "base_model": "openai/whisper-small",
8
+ "language": "ceb",
9
+ "task": "transcribe",
10
+ "test_split_ratio": 0.15,
11
+ "max_input_length_s": 30.0,
12
+ "batch_size": 4,
13
+ "grad_accum_steps": 4,
14
+ "learning_rate": 1e-05,
15
+ "warmup_steps": 100,
16
+ "max_steps": 2000,
17
+ "eval_steps": 200,
18
+ "save_steps": 200,
19
+ "fp16": true,
20
+ "generation_max_length": 225,
21
+ "num_beams": 5
22
  }