Hugging Face's logo

BriereAssia
/
w2v-V2

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Model card Files Community
BriereAssia commited on
Commit
3cab3d9
·
verified ·
1 Parent(s): 5ba78bd

BriereAssia/wav2vec2_finetuned_darija_86_v1

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2363
22
- - Wer: 0.2199
23
 
24
  ## Model description
25
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
- | 3.1759 | 0.1049 | 300 | 0.9128 | 0.8151 |
55
- | 0.7566 | 0.2099 | 600 | 0.6488 | 0.5731 |
56
- | 0.6099 | 0.3148 | 900 | 0.5645 | 0.5568 |
57
- | 0.5685 | 0.4197 | 1200 | 0.4432 | 0.4050 |
58
- | 0.4799 | 0.5247 | 1500 | 0.4051 | 0.3625 |
59
- | 0.4532 | 0.6296 | 1800 | 0.4064 | 0.3344 |
60
- | 0.4197 | 0.7345 | 2100 | 0.3454 | 0.3219 |
61
- | 0.4358 | 0.8395 | 2400 | 0.3409 | 0.3127 |
62
- | 0.3889 | 0.9444 | 2700 | 0.3202 | 0.2738 |
63
- | 0.3637 | 1.0493 | 3000 | 0.2987 | 0.2636 |
64
- | 0.3367 | 1.1542 | 3300 | 0.2833 | 0.2572 |
65
- | 0.2684 | 1.2592 | 3600 | 0.2831 | 0.2455 |
66
- | 0.2909 | 1.3641 | 3900 | 0.2597 | 0.2418 |
67
- | 0.2995 | 1.4690 | 4200 | 0.2508 | 0.2358 |
68
- | 0.287 | 1.5740 | 4500 | 0.2423 | 0.2274 |
69
- | 0.2649 | 1.6789 | 4800 | 0.2363 | 0.2199 |
70
 
71
 
72
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1706
22
+ - Wer: 0.1496
23
 
24
  ## Model description
25
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | 0.3589 | 0.1049 | 300 | 0.2921 | 0.2762 |
55
+ | 0.3512 | 0.2099 | 600 | 0.2855 | 0.2767 |
56
+ | 0.2998 | 0.3148 | 900 | 0.2872 | 0.2550 |
57
+ | 0.3419 | 0.4197 | 1200 | 0.2641 | 0.2620 |
58
+ | 0.2757 | 0.5247 | 1500 | 0.2633 | 0.2332 |
59
+ | 0.2827 | 0.6296 | 1800 | 0.2473 | 0.2090 |
60
+ | 0.265 | 0.7345 | 2100 | 0.2304 | 0.2226 |
61
+ | 0.2985 | 0.8395 | 2400 | 0.2266 | 0.2109 |
62
+ | 0.2555 | 0.9444 | 2700 | 0.2279 | 0.1891 |
63
+ | 0.255 | 1.0493 | 3000 | 0.2129 | 0.1927 |
64
+ | 0.2194 | 1.1542 | 3300 | 0.1991 | 0.1821 |
65
+ | 0.172 | 1.2592 | 3600 | 0.1963 | 0.1710 |
66
+ | 0.2018 | 1.3641 | 3900 | 0.1860 | 0.1724 |
67
+ | 0.2098 | 1.4690 | 4200 | 0.1783 | 0.1717 |
68
+ | 0.1996 | 1.5740 | 4500 | 0.1709 | 0.1563 |
69
+ | 0.1926 | 1.6789 | 4800 | 0.1706 | 0.1496 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eb21cc38a2c01384777ef718122c77e0d380c20126e89926dca134a84c45214
3
  size 2423076960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce958afe68b8a9355b74a9e447dae3b037d9c9d5d84ec25fd04d7632f48b597
3
  size 2423076960