Hugging Face's logo

mutisya
/
wav2vec2-large-mms-1b-turkish-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mutisya commited on
Commit
1ca1eeb
•
1 Parent(s): 8a2d619

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +119 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_11_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2-large-mms-1b-turkish-colab
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_11_0
17
+ type: common_voice_11_0
18
+ config: tr
19
+ split: test
20
+ args: tr
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.2274112463363031
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2-large-mms-1b-turkish-colab
31
+
32
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_11_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1588
35
+ - Wer: 0.2274
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.001
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 100
61
+ - num_epochs: 4
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
66
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
67
+ | 7.9572 | 0.09 | 100 | 0.2279 | 0.2821 |
68
+ | 0.316 | 0.18 | 200 | 0.2011 | 0.2632 |
69
+ | 0.282 | 0.27 | 300 | 0.2027 | 0.2555 |
70
+ | 0.285 | 0.35 | 400 | 0.1978 | 0.2580 |
71
+ | 0.2741 | 0.44 | 500 | 0.1956 | 0.2596 |
72
+ | 0.2643 | 0.53 | 600 | 0.1790 | 0.2487 |
73
+ | 0.2758 | 0.62 | 700 | 0.1791 | 0.2463 |
74
+ | 0.2766 | 0.71 | 800 | 0.1791 | 0.2499 |
75
+ | 0.2733 | 0.8 | 900 | 0.1854 | 0.2610 |
76
+ | 0.2611 | 0.89 | 1000 | 0.1793 | 0.2464 |
77
+ | 0.2582 | 0.97 | 1100 | 0.1734 | 0.2460 |
78
+ | 0.2421 | 1.06 | 1200 | 0.1711 | 0.2408 |
79
+ | 0.2424 | 1.15 | 1300 | 0.1737 | 0.2434 |
80
+ | 0.2455 | 1.24 | 1400 | 0.1761 | 0.2489 |
81
+ | 0.2588 | 1.33 | 1500 | 0.1720 | 0.2410 |
82
+ | 0.2591 | 1.42 | 1600 | 0.1761 | 0.2444 |
83
+ | 0.2497 | 1.51 | 1700 | 0.1696 | 0.2381 |
84
+ | 0.254 | 1.59 | 1800 | 0.1728 | 0.2391 |
85
+ | 0.2479 | 1.68 | 1900 | 0.1724 | 0.2402 |
86
+ | 0.2395 | 1.77 | 2000 | 0.1726 | 0.2389 |
87
+ | 0.237 | 1.86 | 2100 | 0.1710 | 0.2378 |
88
+ | 0.2427 | 1.95 | 2200 | 0.1682 | 0.2348 |
89
+ | 0.2399 | 2.04 | 2300 | 0.1699 | 0.2371 |
90
+ | 0.2457 | 2.13 | 2400 | 0.1695 | 0.2357 |
91
+ | 0.2432 | 2.21 | 2500 | 0.1707 | 0.2387 |
92
+ | 0.229 | 2.3 | 2600 | 0.1687 | 0.2324 |
93
+ | 0.2413 | 2.39 | 2700 | 0.1681 | 0.2354 |
94
+ | 0.2286 | 2.48 | 2800 | 0.1664 | 0.2329 |
95
+ | 0.2405 | 2.57 | 2900 | 0.1646 | 0.2337 |
96
+ | 0.2266 | 2.66 | 3000 | 0.1668 | 0.2341 |
97
+ | 0.2337 | 2.75 | 3100 | 0.1642 | 0.2325 |
98
+ | 0.233 | 2.83 | 3200 | 0.1635 | 0.2301 |
99
+ | 0.2235 | 2.92 | 3300 | 0.1639 | 0.2342 |
100
+ | 0.2395 | 3.01 | 3400 | 0.1630 | 0.2305 |
101
+ | 0.2165 | 3.1 | 3500 | 0.1622 | 0.2305 |
102
+ | 0.2258 | 3.19 | 3600 | 0.1617 | 0.2296 |
103
+ | 0.2288 | 3.28 | 3700 | 0.1608 | 0.2307 |
104
+ | 0.218 | 3.37 | 3800 | 0.1610 | 0.2301 |
105
+ | 0.2242 | 3.45 | 3900 | 0.1604 | 0.2304 |
106
+ | 0.2248 | 3.54 | 4000 | 0.1603 | 0.2273 |
107
+ | 0.2223 | 3.63 | 4100 | 0.1595 | 0.2282 |
108
+ | 0.2161 | 3.72 | 4200 | 0.1593 | 0.2283 |
109
+ | 0.2281 | 3.81 | 4300 | 0.1592 | 0.2278 |
110
+ | 0.2236 | 3.9 | 4400 | 0.1593 | 0.2281 |
111
+ | 0.2277 | 3.99 | 4500 | 0.1588 | 0.2274 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.31.0.dev0
117
+ - Pytorch 2.0.1+cu118
118
+ - Datasets 2.13.1
119
+ - Tokenizers 0.13.3