Hugging Face's logo

fjfur10
/
trocr-finetuned

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
fjfur10 commited on
Commit
47f6f8d
·
verified ·
1 Parent(s): e6be305

fjfur10/trocr-cs682-final3

Browse files
Files changed (3) hide show
  1. README.md +12 -9
  2. config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  library_name: transformers
3
- base_model: microsoft/trocr-small-handwritten
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: trocr-finetuned
8
  results: []
@@ -13,10 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # trocr-finetuned
15
 
16
- This model is a fine-tuned version of [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 11.4593
19
- - Cer: 0.6773
 
20
 
21
  ## Model description
22
 
@@ -46,11 +49,11 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Cer |
50
- |:-------------:|:-----:|:----:|:---------------:|:------:|
51
- | 18.2994 | 1.0 | 12 | 11.5482 | 0.7177 |
52
- | 17.2774 | 2.0 | 24 | 11.4850 | 0.7057 |
53
- | 18.0912 | 3.0 | 36 | 11.4593 | 0.6773 |
54
 
55
 
56
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: microsoft/trocr-small-stage1
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: trocr-finetuned
10
  results: []
 
15
 
16
  # trocr-finetuned
17
 
18
+ This model is a fine-tuned version of [microsoft/trocr-small-stage1](https://huggingface.co/microsoft/trocr-small-stage1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 9.3151
21
+ - Cer: 0.6120
22
+ - Wer: 1.0285
23
 
24
  ## Model description
25
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
54
+ | 12.4053 | 1.0 | 187 | 9.5720 | 0.6938 | 1.1850 |
55
+ | 10.9291 | 2.0 | 374 | 9.3544 | 0.6263 | 1.0732 |
56
+ | 10.6681 | 3.0 | 561 | 9.3151 | 0.6120 | 1.0285 |
57
 
58
 
59
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "microsoft/trocr-small-handwritten",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "microsoft/trocr-small-stage1",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8e41c896f2a06dc24dffc4be90bc83c84dfcd20cb960ff4ebf0d1a1ef371e9
3
  size 246430696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc11cabde7b498d59d83e70860d0aa4987c20550057c061468f17afad3249ea
3
  size 246430696