Hugging Face's logo

smutuvi
/
ndizi-whisper-small-optimized_2

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Model card Files
xet
 Community
smutuvi commited on
Commit
27e2708
·
verified ·
1 Parent(s): 04b9552

Model save

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.8386
22
- - Wer: 0.4075
23
- - Cer: 0.1548
24
 
25
  ## Model description
26
 
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
58
- | 1.5773 | 1.0 | 137 | 1.0771 | 0.5543 | 0.2137 |
59
- | 0.8058 | 2.0 | 274 | 0.7254 | 0.4510 | 0.1662 |
60
- | 0.4218 | 3.0 | 411 | 0.6546 | 0.4252 | 0.1687 |
61
- | 0.27 | 4.0 | 548 | 0.6728 | 0.4134 | 0.1631 |
62
- | 0.1659 | 5.0 | 685 | 0.6983 | 0.4321 | 0.1715 |
63
- | 0.0985 | 6.0 | 822 | 0.7381 | 0.4090 | 0.1536 |
64
- | 0.0641 | 7.0 | 959 | 0.7772 | 0.4100 | 0.1520 |
65
- | 0.0369 | 8.0 | 1096 | 0.8024 | 0.4018 | 0.1528 |
66
- | 0.0199 | 9.0 | 1233 | 0.8279 | 0.4129 | 0.1568 |
67
- | 0.0113 | 10.0 | 1370 | 0.8386 | 0.4075 | 0.1548 |
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8405
22
+ - Wer: 0.4023
23
+ - Cer: 0.1522
24
 
25
  ## Model description
26
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
58
+ | 1.5773 | 1.0 | 137 | 1.0763 | 0.5543 | 0.2140 |
59
+ | 0.8057 | 2.0 | 274 | 0.7256 | 0.4444 | 0.1627 |
60
+ | 0.4219 | 3.0 | 411 | 0.6550 | 0.4226 | 0.1669 |
61
+ | 0.27 | 4.0 | 548 | 0.6721 | 0.4086 | 0.1583 |
62
+ | 0.1647 | 5.0 | 685 | 0.6997 | 0.4299 | 0.1664 |
63
+ | 0.0989 | 6.0 | 822 | 0.7398 | 0.4098 | 0.1526 |
64
+ | 0.0636 | 7.0 | 959 | 0.7776 | 0.4101 | 0.1561 |
65
+ | 0.0376 | 8.0 | 1096 | 0.8047 | 0.3984 | 0.1502 |
66
+ | 0.0207 | 9.0 | 1233 | 0.8293 | 0.4025 | 0.1509 |
67
+ | 0.0114 | 10.0 | 1370 | 0.8405 | 0.4023 | 0.1522 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11073a873ef6ef9c97db50cf84447fe4cfb84b7c227c7975b7c6c3f17acf0bf0
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c74098c4e272262b2021cc614abda137b33dd36841f6b837a613eee148ae30
3
  size 966995080