ojisetyawan
commited on
Commit
•
7c31149
1
Parent(s):
290f123
Training in progress, epoch 3
Browse files
config.json
ADDED
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tarteel-ai/whisper-base-ar-quran",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForAudioClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": null,
|
29 |
+
"id2label": {
|
30 |
+
"0": "01. alif_fathah",
|
31 |
+
"1": "02. alif_kasroh",
|
32 |
+
"2": "03. alif_dommah",
|
33 |
+
"3": "04. ba_fathah",
|
34 |
+
"4": "05. ba_kasroh",
|
35 |
+
"5": "06. ba_dommah",
|
36 |
+
"6": "07. ta_fathah",
|
37 |
+
"7": "08. ta_kasroh",
|
38 |
+
"8": "09. ta_dommah",
|
39 |
+
"9": "10. tsa_fathah",
|
40 |
+
"10": "11. tsa_kasroh",
|
41 |
+
"11": "12. tsa_dommah",
|
42 |
+
"12": "13. jim_fathah",
|
43 |
+
"13": "14. jim_kasroh",
|
44 |
+
"14": "15. jim_dommah",
|
45 |
+
"15": "16. hah_fathah",
|
46 |
+
"16": "17. hah_kasroh",
|
47 |
+
"17": "18. hah_dommah",
|
48 |
+
"18": "19. kha_fathah",
|
49 |
+
"19": "20. kha_kasroh",
|
50 |
+
"20": "21. kha_dommah",
|
51 |
+
"21": "22. dal_fathah",
|
52 |
+
"22": "23. dal_kasroh",
|
53 |
+
"23": "24. dal_dommah",
|
54 |
+
"24": "25. dzal_fathah",
|
55 |
+
"25": "26. dzal_kasroh",
|
56 |
+
"26": "27. dzal_dommah",
|
57 |
+
"27": "28. ra_fathah",
|
58 |
+
"28": "29. ra_kasroh",
|
59 |
+
"29": "30. ra_dommah",
|
60 |
+
"30": "31. zay_fathah",
|
61 |
+
"31": "32. zay_kasroh",
|
62 |
+
"32": "33. zay_dommah",
|
63 |
+
"33": "34. sin_fathah",
|
64 |
+
"34": "35. sin_kasroh",
|
65 |
+
"35": "36. sin_dommah",
|
66 |
+
"36": "37. shin_fathah",
|
67 |
+
"37": "38. shin_kasroh",
|
68 |
+
"38": "39. shin_dommah",
|
69 |
+
"39": "40. sad_fathah",
|
70 |
+
"40": "41. sad_kasroh",
|
71 |
+
"41": "42. sad_dommah",
|
72 |
+
"42": "43. dad_fathah",
|
73 |
+
"43": "44. dad_kasroh",
|
74 |
+
"44": "45. dad_dommah",
|
75 |
+
"45": "46. tah_fathah",
|
76 |
+
"46": "47. tah_kasroh",
|
77 |
+
"47": "48. tah_dommah",
|
78 |
+
"48": "49. zah_fathah",
|
79 |
+
"49": "50. zah_kasroh",
|
80 |
+
"50": "51. zah_dommah",
|
81 |
+
"51": "52. ain_fathah",
|
82 |
+
"52": "53. ain_kasroh",
|
83 |
+
"53": "54. ain_dommah",
|
84 |
+
"54": "55. ghaiin_fathah",
|
85 |
+
"55": "56. ghaiin_kasroh",
|
86 |
+
"56": "57. ghaiin_dommah",
|
87 |
+
"57": "58. fa_fathah",
|
88 |
+
"58": "59. fa_kasroh",
|
89 |
+
"59": "60. fa_dommah",
|
90 |
+
"60": "61. qaf_fathah",
|
91 |
+
"61": "62. qaf_kasroh",
|
92 |
+
"62": "63. qaf_dommah",
|
93 |
+
"63": "64. kaf_fathah",
|
94 |
+
"64": "65. kaf_kasroh",
|
95 |
+
"65": "66. kaf_dommah",
|
96 |
+
"66": "67. lam_fathah",
|
97 |
+
"67": "68. lam_kasroh",
|
98 |
+
"68": "69. lam_dommah",
|
99 |
+
"69": "70. mim_fathah",
|
100 |
+
"70": "71. mim_kasroh",
|
101 |
+
"71": "72. mim_dommah",
|
102 |
+
"72": "73. nun_fathah",
|
103 |
+
"73": "74. nun_kasroh",
|
104 |
+
"74": "75. nun_dommah",
|
105 |
+
"75": "76. Ha_fathah",
|
106 |
+
"76": "77. Ha_kasroh",
|
107 |
+
"77": "78. Ha_dommah",
|
108 |
+
"78": "79. waw_fathah",
|
109 |
+
"79": "80. waw_kasroh",
|
110 |
+
"80": "81. waw_dommah",
|
111 |
+
"81": "82. ya_fathah",
|
112 |
+
"82": "83. ya_kasroh",
|
113 |
+
"83": "84. ya_dommah"
|
114 |
+
},
|
115 |
+
"init_std": 0.02,
|
116 |
+
"is_encoder_decoder": true,
|
117 |
+
"label2id": {
|
118 |
+
"01. alif_fathah": 0,
|
119 |
+
"02. alif_kasroh": 1,
|
120 |
+
"03. alif_dommah": 2,
|
121 |
+
"04. ba_fathah": 3,
|
122 |
+
"05. ba_kasroh": 4,
|
123 |
+
"06. ba_dommah": 5,
|
124 |
+
"07. ta_fathah": 6,
|
125 |
+
"08. ta_kasroh": 7,
|
126 |
+
"09. ta_dommah": 8,
|
127 |
+
"10. tsa_fathah": 9,
|
128 |
+
"11. tsa_kasroh": 10,
|
129 |
+
"12. tsa_dommah": 11,
|
130 |
+
"13. jim_fathah": 12,
|
131 |
+
"14. jim_kasroh": 13,
|
132 |
+
"15. jim_dommah": 14,
|
133 |
+
"16. hah_fathah": 15,
|
134 |
+
"17. hah_kasroh": 16,
|
135 |
+
"18. hah_dommah": 17,
|
136 |
+
"19. kha_fathah": 18,
|
137 |
+
"20. kha_kasroh": 19,
|
138 |
+
"21. kha_dommah": 20,
|
139 |
+
"22. dal_fathah": 21,
|
140 |
+
"23. dal_kasroh": 22,
|
141 |
+
"24. dal_dommah": 23,
|
142 |
+
"25. dzal_fathah": 24,
|
143 |
+
"26. dzal_kasroh": 25,
|
144 |
+
"27. dzal_dommah": 26,
|
145 |
+
"28. ra_fathah": 27,
|
146 |
+
"29. ra_kasroh": 28,
|
147 |
+
"30. ra_dommah": 29,
|
148 |
+
"31. zay_fathah": 30,
|
149 |
+
"32. zay_kasroh": 31,
|
150 |
+
"33. zay_dommah": 32,
|
151 |
+
"34. sin_fathah": 33,
|
152 |
+
"35. sin_kasroh": 34,
|
153 |
+
"36. sin_dommah": 35,
|
154 |
+
"37. shin_fathah": 36,
|
155 |
+
"38. shin_kasroh": 37,
|
156 |
+
"39. shin_dommah": 38,
|
157 |
+
"40. sad_fathah": 39,
|
158 |
+
"41. sad_kasroh": 40,
|
159 |
+
"42. sad_dommah": 41,
|
160 |
+
"43. dad_fathah": 42,
|
161 |
+
"44. dad_kasroh": 43,
|
162 |
+
"45. dad_dommah": 44,
|
163 |
+
"46. tah_fathah": 45,
|
164 |
+
"47. tah_kasroh": 46,
|
165 |
+
"48. tah_dommah": 47,
|
166 |
+
"49. zah_fathah": 48,
|
167 |
+
"50. zah_kasroh": 49,
|
168 |
+
"51. zah_dommah": 50,
|
169 |
+
"52. ain_fathah": 51,
|
170 |
+
"53. ain_kasroh": 52,
|
171 |
+
"54. ain_dommah": 53,
|
172 |
+
"55. ghaiin_fathah": 54,
|
173 |
+
"56. ghaiin_kasroh": 55,
|
174 |
+
"57. ghaiin_dommah": 56,
|
175 |
+
"58. fa_fathah": 57,
|
176 |
+
"59. fa_kasroh": 58,
|
177 |
+
"60. fa_dommah": 59,
|
178 |
+
"61. qaf_fathah": 60,
|
179 |
+
"62. qaf_kasroh": 61,
|
180 |
+
"63. qaf_dommah": 62,
|
181 |
+
"64. kaf_fathah": 63,
|
182 |
+
"65. kaf_kasroh": 64,
|
183 |
+
"66. kaf_dommah": 65,
|
184 |
+
"67. lam_fathah": 66,
|
185 |
+
"68. lam_kasroh": 67,
|
186 |
+
"69. lam_dommah": 68,
|
187 |
+
"70. mim_fathah": 69,
|
188 |
+
"71. mim_kasroh": 70,
|
189 |
+
"72. mim_dommah": 71,
|
190 |
+
"73. nun_fathah": 72,
|
191 |
+
"74. nun_kasroh": 73,
|
192 |
+
"75. nun_dommah": 74,
|
193 |
+
"76. Ha_fathah": 75,
|
194 |
+
"77. Ha_kasroh": 76,
|
195 |
+
"78. Ha_dommah": 77,
|
196 |
+
"79. waw_fathah": 78,
|
197 |
+
"80. waw_kasroh": 79,
|
198 |
+
"81. waw_dommah": 80,
|
199 |
+
"82. ya_fathah": 81,
|
200 |
+
"83. ya_kasroh": 82,
|
201 |
+
"84. ya_dommah": 83
|
202 |
+
},
|
203 |
+
"mask_feature_length": 10,
|
204 |
+
"mask_feature_min_masks": 0,
|
205 |
+
"mask_feature_prob": 0.0,
|
206 |
+
"mask_time_length": 10,
|
207 |
+
"mask_time_min_masks": 2,
|
208 |
+
"mask_time_prob": 0.05,
|
209 |
+
"max_length": 1024,
|
210 |
+
"max_source_positions": 1500,
|
211 |
+
"max_target_positions": 448,
|
212 |
+
"median_filter_width": 7,
|
213 |
+
"model_type": "whisper",
|
214 |
+
"num_hidden_layers": 6,
|
215 |
+
"num_mel_bins": 80,
|
216 |
+
"pad_token_id": 50257,
|
217 |
+
"scale_embedding": false,
|
218 |
+
"torch_dtype": "float32",
|
219 |
+
"transformers_version": "4.46.2",
|
220 |
+
"use_cache": false,
|
221 |
+
"use_weighted_layer_sum": false,
|
222 |
+
"vocab_size": 51865
|
223 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e90fde2fa09ae30a7aefb852773ccb2af009a7c378fb1c54a12b6ace02304779
|
3 |
+
size 82984576
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
runs/Dec02_22-50-35_7f2944423b7c/events.out.tfevents.1733179838.7f2944423b7c.321.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc92abf96de98f4bdb0df0074ecccf399016ef160538d1a40c5563c4a93e6e22
|
3 |
+
size 180419
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fde6556d113284f5f39ae01598b4ff7e15b293fb94119b2dc749b62565ed3c19
|
3 |
+
size 5304
|