Hugging Face's logo

hiba2
/
wav2vec2-large-mms-1b-arabic-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files Metrics Community
hiba2 commited on
Commit
58ec520
·
1 Parent(s): bda53ae

End of training

Browse files
Files changed (4) hide show
  1. README.md +181 -0
  2. adapter.ar_eg.safetensors +3 -0
  3. preprocessor_config.json +1 -0
  4. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - fleurs
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-large-mms-1b-arabic-colab
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: fleurs
18
+ type: fleurs
19
+ config: ar_eg
20
+ split: test
21
+ args: ar_eg
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.2590647661915479
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-large-mms-1b-arabic-colab
32
+
33
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the fleurs dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2922
36
+ - Wer: 0.2591
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 100
62
+ - num_epochs: 20
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
69
+ | 18.9344 | 0.19 | 100 | 17.8048 | 1.0 |
70
+ | 15.6959 | 0.38 | 200 | 14.1448 | 1.0 |
71
+ | 11.9387 | 0.57 | 300 | 9.8417 | 1.0 |
72
+ | 7.554 | 0.76 | 400 | 5.3727 | 1.0 |
73
+ | 4.3953 | 0.95 | 500 | 3.5681 | 1.0 |
74
+ | 3.3533 | 1.14 | 600 | 3.1439 | 1.0 |
75
+ | 2.9309 | 1.33 | 700 | 2.5171 | 0.9987 |
76
+ | 2.1985 | 1.52 | 800 | 1.7128 | 0.8522 |
77
+ | 1.5126 | 1.71 | 900 | 1.1276 | 0.5744 |
78
+ | 1.0376 | 1.9 | 1000 | 0.7830 | 0.4400 |
79
+ | 0.7702 | 2.09 | 1100 | 0.5959 | 0.3765 |
80
+ | 0.6274 | 2.28 | 1200 | 0.4986 | 0.3363 |
81
+ | 0.5423 | 2.47 | 1300 | 0.4473 | 0.3197 |
82
+ | 0.494 | 2.66 | 1400 | 0.4153 | 0.3046 |
83
+ | 0.4372 | 2.85 | 1500 | 0.3940 | 0.2946 |
84
+ | 0.4667 | 3.04 | 1600 | 0.3791 | 0.2887 |
85
+ | 0.4228 | 3.23 | 1700 | 0.3670 | 0.2823 |
86
+ | 0.4177 | 3.42 | 1800 | 0.3571 | 0.2803 |
87
+ | 0.3824 | 3.61 | 1900 | 0.3494 | 0.2789 |
88
+ | 0.4002 | 3.8 | 2000 | 0.3435 | 0.2782 |
89
+ | 0.4112 | 3.99 | 2100 | 0.3385 | 0.2776 |
90
+ | 0.3788 | 4.18 | 2200 | 0.3342 | 0.2768 |
91
+ | 0.4079 | 4.37 | 2300 | 0.3305 | 0.2752 |
92
+ | 0.3939 | 4.56 | 2400 | 0.3271 | 0.2733 |
93
+ | 0.3601 | 4.75 | 2500 | 0.3250 | 0.2724 |
94
+ | 0.3443 | 4.94 | 2600 | 0.3223 | 0.2727 |
95
+ | 0.3723 | 5.13 | 2700 | 0.3200 | 0.2724 |
96
+ | 0.3669 | 5.32 | 2800 | 0.3182 | 0.2704 |
97
+ | 0.3117 | 5.51 | 2900 | 0.3167 | 0.2693 |
98
+ | 0.3658 | 5.7 | 3000 | 0.3150 | 0.2694 |
99
+ | 0.3731 | 5.89 | 3100 | 0.3132 | 0.2683 |
100
+ | 0.3542 | 6.08 | 3200 | 0.3122 | 0.2684 |
101
+ | 0.3667 | 6.27 | 3300 | 0.3108 | 0.2681 |
102
+ | 0.3115 | 6.46 | 3400 | 0.3099 | 0.2671 |
103
+ | 0.3466 | 6.65 | 3500 | 0.3092 | 0.2663 |
104
+ | 0.3497 | 6.84 | 3600 | 0.3082 | 0.2656 |
105
+ | 0.3276 | 7.03 | 3700 | 0.3076 | 0.2667 |
106
+ | 0.3316 | 7.22 | 3800 | 0.3070 | 0.2651 |
107
+ | 0.3324 | 7.41 | 3900 | 0.3060 | 0.2656 |
108
+ | 0.323 | 7.6 | 4000 | 0.3054 | 0.2661 |
109
+ | 0.3411 | 7.79 | 4100 | 0.3045 | 0.2641 |
110
+ | 0.3583 | 7.98 | 4200 | 0.3037 | 0.2649 |
111
+ | 0.3299 | 8.17 | 4300 | 0.3035 | 0.2649 |
112
+ | 0.2899 | 8.37 | 4400 | 0.3030 | 0.2643 |
113
+ | 0.3432 | 8.56 | 4500 | 0.3025 | 0.2651 |
114
+ | 0.3275 | 8.75 | 4600 | 0.3018 | 0.2631 |
115
+ | 0.3652 | 8.94 | 4700 | 0.3011 | 0.2637 |
116
+ | 0.3373 | 9.13 | 4800 | 0.3009 | 0.2626 |
117
+ | 0.3097 | 9.32 | 4900 | 0.3005 | 0.2627 |
118
+ | 0.3163 | 9.51 | 5000 | 0.2997 | 0.2623 |
119
+ | 0.3443 | 9.7 | 5100 | 0.2995 | 0.2623 |
120
+ | 0.346 | 9.89 | 5200 | 0.2989 | 0.2626 |
121
+ | 0.302 | 10.08 | 5300 | 0.2988 | 0.2624 |
122
+ | 0.3252 | 10.27 | 5400 | 0.2983 | 0.2623 |
123
+ | 0.3316 | 10.46 | 5500 | 0.2980 | 0.2632 |
124
+ | 0.3424 | 10.65 | 5600 | 0.2975 | 0.2629 |
125
+ | 0.3205 | 10.84 | 5700 | 0.2977 | 0.2622 |
126
+ | 0.3164 | 11.03 | 5800 | 0.2973 | 0.2618 |
127
+ | 0.3348 | 11.22 | 5900 | 0.2968 | 0.2619 |
128
+ | 0.3236 | 11.41 | 6000 | 0.2967 | 0.2612 |
129
+ | 0.3073 | 11.6 | 6100 | 0.2962 | 0.2627 |
130
+ | 0.3129 | 11.79 | 6200 | 0.2964 | 0.2623 |
131
+ | 0.3319 | 11.98 | 6300 | 0.2961 | 0.2621 |
132
+ | 0.2974 | 12.17 | 6400 | 0.2960 | 0.2613 |
133
+ | 0.3557 | 12.36 | 6500 | 0.2955 | 0.2612 |
134
+ | 0.3068 | 12.55 | 6600 | 0.2957 | 0.2619 |
135
+ | 0.3292 | 12.74 | 6700 | 0.2954 | 0.2619 |
136
+ | 0.3278 | 12.93 | 6800 | 0.2952 | 0.2612 |
137
+ | 0.314 | 13.12 | 6900 | 0.2948 | 0.2614 |
138
+ | 0.3182 | 13.31 | 7000 | 0.2949 | 0.2618 |
139
+ | 0.3322 | 13.5 | 7100 | 0.2948 | 0.2612 |
140
+ | 0.3089 | 13.69 | 7200 | 0.2944 | 0.2616 |
141
+ | 0.3176 | 13.88 | 7300 | 0.2943 | 0.2613 |
142
+ | 0.3025 | 14.07 | 7400 | 0.2942 | 0.2612 |
143
+ | 0.3277 | 14.26 | 7500 | 0.2941 | 0.2613 |
144
+ | 0.3241 | 14.45 | 7600 | 0.2940 | 0.2617 |
145
+ | 0.3084 | 14.64 | 7700 | 0.2938 | 0.2614 |
146
+ | 0.324 | 14.83 | 7800 | 0.2935 | 0.2612 |
147
+ | 0.3229 | 15.02 | 7900 | 0.2934 | 0.2609 |
148
+ | 0.3224 | 15.21 | 8000 | 0.2933 | 0.2602 |
149
+ | 0.2859 | 15.4 | 8100 | 0.2932 | 0.2604 |
150
+ | 0.3173 | 15.59 | 8200 | 0.2931 | 0.2598 |
151
+ | 0.3399 | 15.78 | 8300 | 0.2931 | 0.2602 |
152
+ | 0.3176 | 15.97 | 8400 | 0.2930 | 0.2598 |
153
+ | 0.2993 | 16.16 | 8500 | 0.2930 | 0.2602 |
154
+ | 0.3289 | 16.35 | 8600 | 0.2930 | 0.2598 |
155
+ | 0.3149 | 16.54 | 8700 | 0.2928 | 0.2601 |
156
+ | 0.3172 | 16.73 | 8800 | 0.2927 | 0.2599 |
157
+ | 0.3204 | 16.92 | 8900 | 0.2926 | 0.2597 |
158
+ | 0.3117 | 17.11 | 9000 | 0.2926 | 0.2604 |
159
+ | 0.3051 | 17.3 | 9100 | 0.2927 | 0.2608 |
160
+ | 0.3296 | 17.49 | 9200 | 0.2927 | 0.2604 |
161
+ | 0.309 | 17.68 | 9300 | 0.2926 | 0.2602 |
162
+ | 0.3138 | 17.87 | 9400 | 0.2925 | 0.2593 |
163
+ | 0.2802 | 18.06 | 9500 | 0.2925 | 0.2594 |
164
+ | 0.308 | 18.25 | 9600 | 0.2925 | 0.2593 |
165
+ | 0.3076 | 18.44 | 9700 | 0.2925 | 0.2591 |
166
+ | 0.312 | 18.63 | 9800 | 0.2923 | 0.2592 |
167
+ | 0.31 | 18.82 | 9900 | 0.2923 | 0.2593 |
168
+ | 0.3317 | 19.01 | 10000 | 0.2923 | 0.2592 |
169
+ | 0.3357 | 19.2 | 10100 | 0.2923 | 0.2593 |
170
+ | 0.302 | 19.39 | 10200 | 0.2922 | 0.2596 |
171
+ | 0.294 | 19.58 | 10300 | 0.2923 | 0.2592 |
172
+ | 0.3158 | 19.77 | 10400 | 0.2923 | 0.2593 |
173
+ | 0.3025 | 19.96 | 10500 | 0.2922 | 0.2591 |
174
+
175
+
176
+ ### Framework versions
177
+
178
+ - Transformers 4.35.0.dev0
179
+ - Pytorch 2.1.0+cu118
180
+ - Datasets 2.14.6
181
+ - Tokenizers 0.14.1
adapter.ar_eg.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b747a96c3c8e432733f5b9d9462bd92cdd68a22d773f9a02fbb3bd7a276935b
3
+ size 9177740
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531f181fb22b291c7338c235a0d5ea03cad543cb22d872bd2df38b54691cef37
3
  size 3859514250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ffe7be8f0a73a125a243035cfe5ab1e361690d023799219494836c26607410
3
  size 3859514250