Hugging Face's logo

CasperMuz
/
whisper-base-sna-ven-cleaned

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Shona
Venda
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
CasperMuz commited on
Commit
0752088
·
verified ·
1 Parent(s): f0cd336

End of training

Browse files
Files changed (9) hide show
  1. README.md +75 -0
  2. config.json +152 -0
  3. generation_config.json +276 -0
  4. model.safetensors +3 -0
  5. preprocessor_config.json +14 -0
  6. runs/Aug06_19-39-34_hammitown/events.out.tfevents.1786045174.hammitown.2225709.0 +3 -0
  7. runs/Aug06_20-23-20_hammitown/events.out.tfevents.1786047800.hammitown.2225709.1 +3 -0
  8. runs/Aug06_20-25-13_hammitown/events.out.tfevents.1786047913.hammitown.3223118.0 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - sna
5
+ - ven
6
+ license: apache-2.0
7
+ base_model: openai/whisper-base
8
+ tags:
9
+ - generated_from_trainer
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Base Shona + Tshivenda - Cleaned Data
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # Whisper Base Shona + Tshivenda - Cleaned Data
21
+
22
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Cleaned WAXAL Shona + Swivuriso Tshivenda dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.5899
25
+ - Wer: 48.7657
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 1e-05
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 8
47
+ - seed: 42
48
+ - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 200
51
+ - training_steps: 2000
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
57
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
58
+ | 1.1846 | 0.0882 | 200 | 1.2058 | 79.2304 |
59
+ | 0.8066 | 0.1764 | 400 | 0.8677 | 65.0463 |
60
+ | 0.7158 | 0.2646 | 600 | 0.7538 | 57.1436 |
61
+ | 0.6391 | 0.3527 | 800 | 0.6928 | 55.1938 |
62
+ | 0.6140 | 0.4409 | 1000 | 0.6560 | 52.6030 |
63
+ | 0.5697 | 0.5291 | 1200 | 0.6290 | 51.2560 |
64
+ | 0.5357 | 0.6173 | 1400 | 0.6114 | 48.9857 |
65
+ | 0.5352 | 0.7055 | 1600 | 0.5992 | 48.9450 |
66
+ | 0.5247 | 0.7937 | 1800 | 0.5924 | 48.7657 |
67
+ | 0.5443 | 0.8818 | 2000 | 0.5899 | 48.7657 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 5.14.1
73
+ - Pytorch 2.13.0+cu130
74
+ - Datasets 5.0.1
75
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 512,
16
+ "decoder_attention_heads": 8,
17
+ "decoder_ffn_dim": 2048,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 50258,
21
+ "dropout": 0.0,
22
+ "dtype": "float32",
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": [
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
+ 50358,
142
+ 50359,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
+ "tie_word_embeddings": true,
148
+ "transformers_version": "5.14.1",
149
+ "use_cache": false,
150
+ "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
152
+ }
generation_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
53
+ "is_multilingual": true,
54
+ "lang_to_id": {
55
+ "<|af|>": 50327,
56
+ "<|am|>": 50334,
57
+ "<|ar|>": 50272,
58
+ "<|as|>": 50350,
59
+ "<|az|>": 50304,
60
+ "<|ba|>": 50355,
61
+ "<|be|>": 50330,
62
+ "<|bg|>": 50292,
63
+ "<|bn|>": 50302,
64
+ "<|bo|>": 50347,
65
+ "<|br|>": 50309,
66
+ "<|bs|>": 50315,
67
+ "<|ca|>": 50270,
68
+ "<|cs|>": 50283,
69
+ "<|cy|>": 50297,
70
+ "<|da|>": 50285,
71
+ "<|de|>": 50261,
72
+ "<|el|>": 50281,
73
+ "<|en|>": 50259,
74
+ "<|es|>": 50262,
75
+ "<|et|>": 50307,
76
+ "<|eu|>": 50310,
77
+ "<|fa|>": 50300,
78
+ "<|fi|>": 50277,
79
+ "<|fo|>": 50338,
80
+ "<|fr|>": 50265,
81
+ "<|gl|>": 50319,
82
+ "<|gu|>": 50333,
83
+ "<|haw|>": 50352,
84
+ "<|ha|>": 50354,
85
+ "<|he|>": 50279,
86
+ "<|hi|>": 50276,
87
+ "<|hr|>": 50291,
88
+ "<|ht|>": 50339,
89
+ "<|hu|>": 50286,
90
+ "<|hy|>": 50312,
91
+ "<|id|>": 50275,
92
+ "<|is|>": 50311,
93
+ "<|it|>": 50274,
94
+ "<|ja|>": 50266,
95
+ "<|jw|>": 50356,
96
+ "<|ka|>": 50329,
97
+ "<|kk|>": 50316,
98
+ "<|km|>": 50323,
99
+ "<|kn|>": 50306,
100
+ "<|ko|>": 50264,
101
+ "<|la|>": 50294,
102
+ "<|lb|>": 50345,
103
+ "<|ln|>": 50353,
104
+ "<|lo|>": 50336,
105
+ "<|lt|>": 50293,
106
+ "<|lv|>": 50301,
107
+ "<|mg|>": 50349,
108
+ "<|mi|>": 50295,
109
+ "<|mk|>": 50308,
110
+ "<|ml|>": 50296,
111
+ "<|mn|>": 50314,
112
+ "<|mr|>": 50320,
113
+ "<|ms|>": 50282,
114
+ "<|mt|>": 50343,
115
+ "<|my|>": 50346,
116
+ "<|ne|>": 50313,
117
+ "<|nl|>": 50271,
118
+ "<|nn|>": 50342,
119
+ "<|no|>": 50288,
120
+ "<|oc|>": 50328,
121
+ "<|pa|>": 50321,
122
+ "<|pl|>": 50269,
123
+ "<|ps|>": 50340,
124
+ "<|pt|>": 50267,
125
+ "<|ro|>": 50284,
126
+ "<|ru|>": 50263,
127
+ "<|sa|>": 50344,
128
+ "<|sd|>": 50332,
129
+ "<|si|>": 50322,
130
+ "<|sk|>": 50298,
131
+ "<|sl|>": 50305,
132
+ "<|sn|>": 50324,
133
+ "<|so|>": 50326,
134
+ "<|sq|>": 50317,
135
+ "<|sr|>": 50303,
136
+ "<|su|>": 50357,
137
+ "<|sv|>": 50273,
138
+ "<|sw|>": 50318,
139
+ "<|ta|>": 50287,
140
+ "<|te|>": 50299,
141
+ "<|tg|>": 50331,
142
+ "<|th|>": 50289,
143
+ "<|tk|>": 50341,
144
+ "<|tl|>": 50348,
145
+ "<|tr|>": 50268,
146
+ "<|tt|>": 50351,
147
+ "<|uk|>": 50280,
148
+ "<|ur|>": 50290,
149
+ "<|uz|>": 50337,
150
+ "<|vi|>": 50278,
151
+ "<|yi|>": 50335,
152
+ "<|yo|>": 50325,
153
+ "<|zh|>": 50260
154
+ },
155
+ "language": "Shona",
156
+ "length_penalty": 1.0,
157
+ "max_initial_timestamp_index": 50,
158
+ "max_length": 448,
159
+ "min_length": 0,
160
+ "no_repeat_ngram_size": 0,
161
+ "no_timestamps_token_id": 50363,
162
+ "num_assistant_tokens": 20,
163
+ "num_assistant_tokens_schedule": "constant",
164
+ "num_beam_groups": 1,
165
+ "num_beams": 1,
166
+ "num_return_sequences": 1,
167
+ "output_scores": false,
168
+ "pad_token_id": 50257,
169
+ "prev_sot_token_id": 50361,
170
+ "remove_invalid_values": false,
171
+ "repetition_penalty": 1.0,
172
+ "return_dict_in_generate": false,
173
+ "return_timestamps": false,
174
+ "suppress_tokens": [
175
+ 1,
176
+ 2,
177
+ 7,
178
+ 8,
179
+ 9,
180
+ 10,
181
+ 14,
182
+ 25,
183
+ 26,
184
+ 27,
185
+ 28,
186
+ 29,
187
+ 31,
188
+ 58,
189
+ 59,
190
+ 60,
191
+ 61,
192
+ 62,
193
+ 63,
194
+ 90,
195
+ 91,
196
+ 92,
197
+ 93,
198
+ 359,
199
+ 503,
200
+ 522,
201
+ 542,
202
+ 873,
203
+ 893,
204
+ 902,
205
+ 918,
206
+ 922,
207
+ 931,
208
+ 1350,
209
+ 1853,
210
+ 1982,
211
+ 2460,
212
+ 2627,
213
+ 3246,
214
+ 3253,
215
+ 3268,
216
+ 3536,
217
+ 3846,
218
+ 3961,
219
+ 4183,
220
+ 4667,
221
+ 6585,
222
+ 6647,
223
+ 7273,
224
+ 9061,
225
+ 9383,
226
+ 10428,
227
+ 10929,
228
+ 11938,
229
+ 12033,
230
+ 12331,
231
+ 12562,
232
+ 13793,
233
+ 14157,
234
+ 14635,
235
+ 15265,
236
+ 15618,
237
+ 16553,
238
+ 16604,
239
+ 18362,
240
+ 18956,
241
+ 20075,
242
+ 21675,
243
+ 22520,
244
+ 26130,
245
+ 26161,
246
+ 26435,
247
+ 28279,
248
+ 29464,
249
+ 31650,
250
+ 32302,
251
+ 32470,
252
+ 36865,
253
+ 42863,
254
+ 47425,
255
+ 49870,
256
+ 50254,
257
+ 50258,
258
+ 50358,
259
+ 50359,
260
+ 50360,
261
+ 50361,
262
+ 50362
263
+ ],
264
+ "target_lookbehind": 10,
265
+ "task": "transcribe",
266
+ "task_to_id": {
267
+ "transcribe": 50359,
268
+ "translate": 50358
269
+ },
270
+ "temperature": 1.0,
271
+ "top_k": 50,
272
+ "top_p": 1.0,
273
+ "transformers_version": "5.14.1",
274
+ "typical_p": 1.0,
275
+ "use_cache": true
276
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266c6935bd8ae1ea1e23c34dc36d0c7dbee202f91868d9a2471c209e9c28b79f
3
+ size 290403936
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
+ }
runs/Aug06_19-39-34_hammitown/events.out.tfevents.1786045174.hammitown.2225709.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42ffa1b4e3747ec3414ff39a63a75708e4dac3bca898332be1fe115d05d8a9a
3
+ size 12048
runs/Aug06_20-23-20_hammitown/events.out.tfevents.1786047800.hammitown.2225709.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6a1f07b5bedfdcccfa74c0d0fd1bdbc446d8adeb7882ba73972e20c05078d6
3
+ size 6671
runs/Aug06_20-25-13_hammitown/events.out.tfevents.1786047913.hammitown.3223118.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64db63697a348707e2ad7c345801309fdfc6a0bb4db0976b25b8eda768ed6d4d
3
+ size 26444
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127571f9ac23066538430d3188149e6e6bd22ba4f040bb8689d4c77b7f83af9a
3
+ size 5393
Free AI Image Generator No sign-up. Instant results. Open Now