myandev thantzinphyo commited on
Commit
de9f257
·
0 Parent(s):

Duplicate from thantzinphyo/Whisper-Base-ASR

Browse files

Co-authored-by: Thant Zin Phyo <thantzinphyo@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - my
4
+ license: apache-2.0
5
+ tags:
6
+ - audio
7
+ - automatic-speech-recognition
8
+ - speech
9
+ - whisper
10
+ - burmese
11
+ datasets:
12
+ - thantzinphyo/Burmese-Daily-Dialogue-Corpus
13
+ metrics:
14
+ - cer
15
+ - wer
16
+ - chrf
17
+ pipeline_tag: automatic-speech-recognition
18
+ base_model:
19
+ - openai/whisper-base
20
+ model-index:
21
+ - name: Whisper-Base-ASR
22
+ results:
23
+ - task:
24
+ type: automatic-speech-recognition
25
+ name: Automatic Speech Recognition
26
+ dataset:
27
+ name: Burmese Daily Dialogue Corpus (BDDC)
28
+ type: thantzinphyo/Burmese-Daily-Dialogue-Corpus
29
+ metrics:
30
+ - name: Validation CER
31
+ type: cer
32
+ value: 4.43
33
+ - name: Validation WER
34
+ type: wer
35
+ value: 26.55
36
+ - name: Validation chrF
37
+ type: chrf
38
+ value: 91.94
39
+ - name: Test CER (Unseen Speakers)
40
+ type: cer
41
+ value: 8.55
42
+ - name: Test WER (Unseen Speakers)
43
+ type: wer
44
+ value: 36.29
45
+ - name: Test chrF (Unseen Speakers)
46
+ type: chrf
47
+ value: 83.71
48
+ ---
49
+
50
+
51
+ # Whisper-Base-ASR ( Burmese )
52
+
53
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) for Automatic Speech Recognition (ASR) in Burmese .
54
+
55
+ ## Model Overview
56
+
57
+ - **Architecture:** Whisper (Base)
58
+ - **Parameters:** ~74M
59
+ - **Task:** Automatic Speech Recognition (ASR)
60
+ - **Language:** Burmese (`my`)
61
+ - **Sampling Rate:** 16,000 Hz (Mono)
62
+
63
+ ## Dataset Details
64
+
65
+ The model was trained on a standardized, high-quality Burmese speech corpus:
66
+
67
+ - **Total Duration:** ~22 Hours of audio
68
+ - **Total Utterances:** 24,560 WAV files (16 kHz, 16-bit PCM, Mono)
69
+ - **Total Speakers:** 13 Synthetic Burmese Speakers
70
+ - **Speakers:** ပီယ ၊ ဝါစာ ၊ သီရိ ၊ ဒီပ ၊ အက္ခရာ ၊ သဒ္ဒါ ၊ သရ ၊ တာရာ ၊ ကဝိ ၊ သုတ ၊ ပသာဒ ၊ ဂီတ ၊ နန္ဒ
71
+ - **Training & Validation:** 11 speakers (20,699 train utterances, 2,300 validation utterances)
72
+ - **Test Set (Held-Out):** 2 unseen speakers ( ဂီတ & နန္ဒ , 1,561 utterances )
73
+ - **Text Preprocessing:** Standardized Myanmar Unicode (`\u1000-\u109F`) with unified word segmentation and punctuation removal. The held-out test split evaluates zero-shot acoustic generalization across completely unseen voices.
74
+
75
+ ## Training Configuration
76
+
77
+ | Parameter | Value |
78
+ | :--- | :--- |
79
+ | Effective Batch Size | 64 (16 per device x 4 gradient accumulation) |
80
+ | Peak Learning Rate | 1.0e-4 |
81
+ | Learning Rate Scheduler | Cosine |
82
+ | Warmup Steps | 200 |
83
+ | Total Steps | 2,000 (~12.37 Epochs) |
84
+ | Mixed Precision | BF16 |
85
+ | Weight Decay | 0.01 |
86
+ | Gradient Checkpointing | Enabled |
87
+ | Augmentation | None |
88
+
89
+ ## Evaluation Results
90
+
91
+ | Stage / Evaluation | Step | Train Loss | Val Loss | WER (%) | CER (%) | SER (%) | DER (%) | IER (%) | chrF |
92
+ | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
93
+ | Baseline (Untrained) | 0 | - | - | 753.85 | 437.94 | 100.00 | 7.69 | 653.85 | 0.00 |
94
+ | Validation Set | 250 | 0.6374 | 0.0725 | 47.99 | 10.33 | 93.57 | 10.36 | 2.65 | 81.45 |
95
+ | Validation Set | 500 | 0.2351 | 0.0453 | 37.15 | 6.92 | 87.52 | 6.12 | 2.81 | 86.66 |
96
+ | Validation Set | 750 | 0.1369 | 0.0417 | 31.71 | 5.70 | 81.61 | 3.60 | 4.19 | 89.08 |
97
+ | Validation Set | 1000 | 0.0482 | 0.0416 | 28.87 | 5.00 | 76.74 | 4.22 | 3.29 | 91.07 |
98
+ | Validation Set | 1250 | 0.0252 | 0.0435 | 28.18 | 4.79 | 76.74 | 3.72 | 3.31 | 91.23 |
99
+ | Validation Set | 1500 | 0.0039 | 0.0476 | 28.06 | 4.69 | 78.48 | 3.81 | 2.94 | 91.40 |
100
+ | Validation Set | 1750 | 0.0007 | 0.0502 | 26.91 | 4.47 | 76.30 | 3.26 | 3.44 | 91.79 |
101
+ | Validation Set | 2000 | 0.0004 | 0.0507 | 26.55 | 4.43 | 75.65 | 3.31 | 3.37 | 91.94 |
102
+ | **UNSEEN TEST (Final)** | **Final** | **-** | **-** | **36.29** | **8.55** | **94.30** | **5.40** | **3.22** | **83.71** |
103
+
104
+ ## Usage
105
+
106
+ ```python
107
+ import torch
108
+ from transformers import pipeline
109
+
110
+ pipe = pipeline(
111
+ 'automatic-speech-recognition',
112
+ model='thantzinphyo/Whisper-Base-ASR',
113
+ device='cuda:0' if torch.cuda.is_available() else 'cpu',
114
+ )
115
+
116
+ output = pipe('audio.wav', generate_kwargs={'language': 'burmese', 'task': 'transcribe'})
117
+ print(output['text'])
118
+ ```
119
+
120
+ ## License
121
+
122
+ Apache-2.0
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 512,
12
+ "decoder_attention_heads": 8,
13
+ "decoder_ffn_dim": 2048,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 8,
20
+ "encoder_ffn_dim": 2048,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 6,
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": 6,
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
+ }
generation_config.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "assistant_confidence_threshold": 0.4,
37
+ "assistant_lookbehind": 10,
38
+ "begin_suppress_tokens": [
39
+ 220,
40
+ 50257
41
+ ],
42
+ "bos_token_id": 50257,
43
+ "decoder_start_token_id": 50258,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "early_stopping": false,
47
+ "encoder_no_repeat_ngram_size": 0,
48
+ "encoder_repetition_penalty": 1.0,
49
+ "eos_token_id": 50257,
50
+ "epsilon_cutoff": 0.0,
51
+ "eta_cutoff": 0.0,
52
+ "forced_decoder_ids": [
53
+ [
54
+ 1,
55
+ 50346
56
+ ],
57
+ [
58
+ 2,
59
+ 50359
60
+ ],
61
+ [
62
+ 3,
63
+ 50363
64
+ ]
65
+ ],
66
+ "is_multilingual": true,
67
+ "lang_to_id": {
68
+ "<|af|>": 50327,
69
+ "<|am|>": 50334,
70
+ "<|ar|>": 50272,
71
+ "<|as|>": 50350,
72
+ "<|az|>": 50304,
73
+ "<|ba|>": 50355,
74
+ "<|be|>": 50330,
75
+ "<|bg|>": 50292,
76
+ "<|bn|>": 50302,
77
+ "<|bo|>": 50347,
78
+ "<|br|>": 50309,
79
+ "<|bs|>": 50315,
80
+ "<|ca|>": 50270,
81
+ "<|cs|>": 50283,
82
+ "<|cy|>": 50297,
83
+ "<|da|>": 50285,
84
+ "<|de|>": 50261,
85
+ "<|el|>": 50281,
86
+ "<|en|>": 50259,
87
+ "<|es|>": 50262,
88
+ "<|et|>": 50307,
89
+ "<|eu|>": 50310,
90
+ "<|fa|>": 50300,
91
+ "<|fi|>": 50277,
92
+ "<|fo|>": 50338,
93
+ "<|fr|>": 50265,
94
+ "<|gl|>": 50319,
95
+ "<|gu|>": 50333,
96
+ "<|haw|>": 50352,
97
+ "<|ha|>": 50354,
98
+ "<|he|>": 50279,
99
+ "<|hi|>": 50276,
100
+ "<|hr|>": 50291,
101
+ "<|ht|>": 50339,
102
+ "<|hu|>": 50286,
103
+ "<|hy|>": 50312,
104
+ "<|id|>": 50275,
105
+ "<|is|>": 50311,
106
+ "<|it|>": 50274,
107
+ "<|ja|>": 50266,
108
+ "<|jw|>": 50356,
109
+ "<|ka|>": 50329,
110
+ "<|kk|>": 50316,
111
+ "<|km|>": 50323,
112
+ "<|kn|>": 50306,
113
+ "<|ko|>": 50264,
114
+ "<|la|>": 50294,
115
+ "<|lb|>": 50345,
116
+ "<|ln|>": 50353,
117
+ "<|lo|>": 50336,
118
+ "<|lt|>": 50293,
119
+ "<|lv|>": 50301,
120
+ "<|mg|>": 50349,
121
+ "<|mi|>": 50295,
122
+ "<|mk|>": 50308,
123
+ "<|ml|>": 50296,
124
+ "<|mn|>": 50314,
125
+ "<|mr|>": 50320,
126
+ "<|ms|>": 50282,
127
+ "<|mt|>": 50343,
128
+ "<|my|>": 50346,
129
+ "<|ne|>": 50313,
130
+ "<|nl|>": 50271,
131
+ "<|nn|>": 50342,
132
+ "<|no|>": 50288,
133
+ "<|oc|>": 50328,
134
+ "<|pa|>": 50321,
135
+ "<|pl|>": 50269,
136
+ "<|ps|>": 50340,
137
+ "<|pt|>": 50267,
138
+ "<|ro|>": 50284,
139
+ "<|ru|>": 50263,
140
+ "<|sa|>": 50344,
141
+ "<|sd|>": 50332,
142
+ "<|si|>": 50322,
143
+ "<|sk|>": 50298,
144
+ "<|sl|>": 50305,
145
+ "<|sn|>": 50324,
146
+ "<|so|>": 50326,
147
+ "<|sq|>": 50317,
148
+ "<|sr|>": 50303,
149
+ "<|su|>": 50357,
150
+ "<|sv|>": 50273,
151
+ "<|sw|>": 50318,
152
+ "<|ta|>": 50287,
153
+ "<|te|>": 50299,
154
+ "<|tg|>": 50331,
155
+ "<|th|>": 50289,
156
+ "<|tk|>": 50341,
157
+ "<|tl|>": 50348,
158
+ "<|tr|>": 50268,
159
+ "<|tt|>": 50351,
160
+ "<|uk|>": 50280,
161
+ "<|ur|>": 50290,
162
+ "<|uz|>": 50337,
163
+ "<|vi|>": 50278,
164
+ "<|yi|>": 50335,
165
+ "<|yo|>": 50325,
166
+ "<|zh|>": 50260
167
+ },
168
+ "language": "my",
169
+ "length_penalty": 1.0,
170
+ "max_initial_timestamp_index": 50,
171
+ "max_length": 448,
172
+ "min_length": 0,
173
+ "no_repeat_ngram_size": 0,
174
+ "no_timestamps_token_id": 50363,
175
+ "num_assistant_tokens": 20,
176
+ "num_assistant_tokens_schedule": "constant",
177
+ "num_beam_groups": 1,
178
+ "num_beams": 1,
179
+ "num_return_sequences": 1,
180
+ "output_scores": false,
181
+ "pad_token_id": 50257,
182
+ "prev_sot_token_id": 50361,
183
+ "remove_invalid_values": false,
184
+ "repetition_penalty": 1.0,
185
+ "return_dict_in_generate": false,
186
+ "return_timestamps": false,
187
+ "suppress_tokens": [
188
+ 1,
189
+ 2,
190
+ 7,
191
+ 8,
192
+ 9,
193
+ 10,
194
+ 14,
195
+ 25,
196
+ 26,
197
+ 27,
198
+ 28,
199
+ 29,
200
+ 31,
201
+ 58,
202
+ 59,
203
+ 60,
204
+ 61,
205
+ 62,
206
+ 63,
207
+ 90,
208
+ 91,
209
+ 92,
210
+ 93,
211
+ 359,
212
+ 503,
213
+ 522,
214
+ 542,
215
+ 873,
216
+ 893,
217
+ 902,
218
+ 918,
219
+ 922,
220
+ 931,
221
+ 1350,
222
+ 1853,
223
+ 1982,
224
+ 2460,
225
+ 2627,
226
+ 3246,
227
+ 3253,
228
+ 3268,
229
+ 3536,
230
+ 3846,
231
+ 3961,
232
+ 4183,
233
+ 4667,
234
+ 6585,
235
+ 6647,
236
+ 7273,
237
+ 9061,
238
+ 9383,
239
+ 10428,
240
+ 10929,
241
+ 11938,
242
+ 12033,
243
+ 12331,
244
+ 12562,
245
+ 13793,
246
+ 14157,
247
+ 14635,
248
+ 15265,
249
+ 15618,
250
+ 16553,
251
+ 16604,
252
+ 18362,
253
+ 18956,
254
+ 20075,
255
+ 21675,
256
+ 22520,
257
+ 26130,
258
+ 26161,
259
+ 26435,
260
+ 28279,
261
+ 29464,
262
+ 31650,
263
+ 32302,
264
+ 32470,
265
+ 36865,
266
+ 42863,
267
+ 47425,
268
+ 49870,
269
+ 50254,
270
+ 50258,
271
+ 50358,
272
+ 50359,
273
+ 50360,
274
+ 50361,
275
+ 50362
276
+ ],
277
+ "target_lookbehind": 10,
278
+ "task": "transcribe",
279
+ "task_to_id": {
280
+ "transcribe": 50359,
281
+ "translate": 50358
282
+ },
283
+ "temperature": 1.0,
284
+ "top_k": 50,
285
+ "top_p": 1.0,
286
+ "transformers_version": "5.0.0",
287
+ "typical_p": 1.0,
288
+ "use_cache": true
289
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1f66877dba1bdf9dcccb956a797d443e107820ac5731a0172b827af6db360c
3
+ size 290403936
processor_config.json ADDED
@@ -0,0 +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
+ }
runs/Sep24_05-21-17_a01cb46400e4/events.out.tfevents.1790227277.a01cb46400e4.58.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13d4a4ea2723467813a8ce40f157795ea023f87edb3e1bef3c2d70db130a7bb
3
+ size 27178
runs/Sep24_05-21-17_a01cb46400e4/events.out.tfevents.1790256790.a01cb46400e4.58.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9388d33082f556ddd93769d153a8e75da58cef9996168e07c7906b0a8acbe2d
3
+ size 689
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "my",
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e5beaeeaf05a26445e2337d017557dea7206788900c47044d84a21208047d8
3
+ size 5393