macarious commited on
Commit
b0b63c3
·
1 Parent(s): e508a64

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -6
README.md CHANGED
@@ -1,12 +1,9 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
  tags:
6
- - audio
7
- - speech
8
- - wav2vec2
9
  - generated_from_trainer
 
 
10
  model-index:
11
  - name: torgo_xlsr_finetune_M02_keep_all
12
  results: []
@@ -17,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # torgo_xlsr_finetune_M02_keep_all
19
 
20
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the torgo dataset.
 
 
 
21
 
22
  ## Model description
23
 
@@ -47,6 +47,47 @@ The following hyperparameters were used during training:
47
  - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 20
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  ### Framework versions
51
 
52
  - Transformers 4.26.1
 
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
 
 
4
  - generated_from_trainer
5
+ metrics:
6
+ - wer
7
  model-index:
8
  - name: torgo_xlsr_finetune_M02_keep_all
9
  results: []
 
14
 
15
  # torgo_xlsr_finetune_M02_keep_all
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.6539
20
+ - Wer: 0.2436
21
 
22
  ## Model description
23
 
 
47
  - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 20
49
 
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 3.5043 | 0.56 | 1000 | 3.3139 | 1.0 |
55
+ | 2.1248 | 1.12 | 2000 | 1.9926 | 0.8898 |
56
+ | 1.0178 | 1.67 | 3000 | 1.5324 | 0.6683 |
57
+ | 0.7315 | 2.23 | 4000 | 1.7989 | 0.5959 |
58
+ | 0.6289 | 2.79 | 5000 | 1.3984 | 0.4987 |
59
+ | 0.5123 | 3.35 | 6000 | 1.2977 | 0.4228 |
60
+ | 0.4751 | 3.91 | 7000 | 1.3967 | 0.3988 |
61
+ | 0.4354 | 4.47 | 8000 | 1.5080 | 0.4274 |
62
+ | 0.3817 | 5.03 | 9000 | 1.7897 | 0.4014 |
63
+ | 0.3758 | 5.58 | 10000 | 1.3421 | 0.3385 |
64
+ | 0.358 | 6.14 | 11000 | 1.6429 | 0.3427 |
65
+ | 0.3083 | 6.7 | 12000 | 1.2683 | 0.3084 |
66
+ | 0.2805 | 7.26 | 13000 | 1.7095 | 0.3122 |
67
+ | 0.2856 | 7.82 | 14000 | 1.7918 | 0.3317 |
68
+ | 0.2574 | 8.38 | 15000 | 1.5411 | 0.2947 |
69
+ | 0.2495 | 8.93 | 16000 | 1.4551 | 0.2997 |
70
+ | 0.2651 | 9.49 | 17000 | 1.5073 | 0.2825 |
71
+ | 0.2517 | 10.05 | 18000 | 1.6405 | 0.2920 |
72
+ | 0.2274 | 10.61 | 19000 | 1.4440 | 0.2604 |
73
+ | 0.2278 | 11.17 | 20000 | 1.4020 | 0.2875 |
74
+ | 0.2472 | 11.73 | 21000 | 1.6264 | 0.2897 |
75
+ | 0.1875 | 12.28 | 22000 | 1.5901 | 0.2783 |
76
+ | 0.175 | 12.84 | 23000 | 1.4056 | 0.2501 |
77
+ | 0.1751 | 13.4 | 24000 | 1.4809 | 0.2631 |
78
+ | 0.1607 | 13.96 | 25000 | 1.4363 | 0.2551 |
79
+ | 0.1712 | 14.52 | 26000 | 1.6480 | 0.2524 |
80
+ | 0.1581 | 15.08 | 27000 | 1.5084 | 0.2615 |
81
+ | 0.1623 | 15.63 | 28000 | 1.4066 | 0.2482 |
82
+ | 0.1397 | 16.19 | 29000 | 1.7111 | 0.2619 |
83
+ | 0.1536 | 16.75 | 30000 | 1.4691 | 0.2402 |
84
+ | 0.1343 | 17.31 | 31000 | 1.5406 | 0.2329 |
85
+ | 0.1428 | 17.87 | 32000 | 1.5261 | 0.2413 |
86
+ | 0.1125 | 18.43 | 33000 | 1.6416 | 0.2337 |
87
+ | 0.1214 | 18.98 | 34000 | 1.6803 | 0.2425 |
88
+ | 0.124 | 19.54 | 35000 | 1.6539 | 0.2436 |
89
+
90
+
91
  ### Framework versions
92
 
93
  - Transformers 4.26.1