Hugging Face's logo

dh-unibe
/
trocr-kurrent

Image-Text-to-Text
Transformers
PyTorch
Safetensors
German
vision-encoder-decoder
image-to-text
trocr
kurrent
ocr
htr
19th century
Model card Files
xet
Community
3
Jonas Widmer commited on
Commit
2a3575e
·
1 Parent(s): e93cc39

new model version

Browse files
Files changed (10) hide show
  1. config.json +8 -3
  2. generation_config.json +13 -0
  3. optimizer.pt +2 -2
  4. preprocessor_config.json +7 -2
  5. pytorch_model.bin +1 -1
  6. rng_state.pth +2 -2
  7. scaler.pt +1 -1
  8. scheduler.pt +1 -1
  9. trainer_state.json +0 -0
  10. training_args.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_commit_hash": "69659a277424eb381574e4952f3b3fa3440a419b",
3
  "_name_or_path": "microsoft/trocr-base-handwritten",
4
  "architectures": [
5
  "VisionEncoderDecoderModel"
@@ -12,6 +12,7 @@
12
  "architectures": null,
13
  "attention_dropout": 0.0,
14
  "bad_words_ids": null,
 
15
  "bos_token_id": 0,
16
  "chunk_size_feed_forward": 0,
17
  "classifier_dropout": 0.0,
@@ -66,6 +67,7 @@
66
  "return_dict_in_generate": false,
67
  "scale_embedding": false,
68
  "sep_token_id": null,
 
69
  "task_specific_params": null,
70
  "temperature": 1.0,
71
  "tf_legacy_loss": false,
@@ -76,7 +78,7 @@
76
  "top_p": 1.0,
77
  "torch_dtype": null,
78
  "torchscript": false,
79
- "transformers_version": "4.22.2",
80
  "typical_p": 1.0,
81
  "use_bfloat16": false,
82
  "use_cache": false,
@@ -91,6 +93,7 @@
91
  "architectures": null,
92
  "attention_probs_dropout_prob": 0.0,
93
  "bad_words_ids": null,
 
94
  "bos_token_id": null,
95
  "chunk_size_feed_forward": 0,
96
  "cross_attention_hidden_size": null,
@@ -147,6 +150,7 @@
147
  "return_dict": true,
148
  "return_dict_in_generate": false,
149
  "sep_token_id": null,
 
150
  "task_specific_params": null,
151
  "temperature": 1.0,
152
  "tf_legacy_loss": false,
@@ -157,7 +161,7 @@
157
  "top_p": 1.0,
158
  "torch_dtype": null,
159
  "torchscript": false,
160
- "transformers_version": "4.22.2",
161
  "typical_p": 1.0,
162
  "use_bfloat16": false
163
  },
@@ -168,6 +172,7 @@
168
  "model_type": "vision-encoder-decoder",
169
  "num_beams": 4,
170
  "pad_token_id": 1,
 
171
  "tie_word_embeddings": false,
172
  "torch_dtype": "float32",
173
  "transformers_version": null,
 
1
  {
2
+ "_commit_hash": "0cc7abaad739c7902dabd562356c7e6a7be834ea",
3
  "_name_or_path": "microsoft/trocr-base-handwritten",
4
  "architectures": [
5
  "VisionEncoderDecoderModel"
 
12
  "architectures": null,
13
  "attention_dropout": 0.0,
14
  "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
  "bos_token_id": 0,
17
  "chunk_size_feed_forward": 0,
18
  "classifier_dropout": 0.0,
 
67
  "return_dict_in_generate": false,
68
  "scale_embedding": false,
69
  "sep_token_id": null,
70
+ "suppress_tokens": null,
71
  "task_specific_params": null,
72
  "temperature": 1.0,
73
  "tf_legacy_loss": false,
 
78
  "top_p": 1.0,
79
  "torch_dtype": null,
80
  "torchscript": false,
81
+ "transformers_version": "4.26.0",
82
  "typical_p": 1.0,
83
  "use_bfloat16": false,
84
  "use_cache": false,
 
93
  "architectures": null,
94
  "attention_probs_dropout_prob": 0.0,
95
  "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
  "bos_token_id": null,
98
  "chunk_size_feed_forward": 0,
99
  "cross_attention_hidden_size": null,
 
150
  "return_dict": true,
151
  "return_dict_in_generate": false,
152
  "sep_token_id": null,
153
+ "suppress_tokens": null,
154
  "task_specific_params": null,
155
  "temperature": 1.0,
156
  "tf_legacy_loss": false,
 
161
  "top_p": 1.0,
162
  "torch_dtype": null,
163
  "torchscript": false,
164
+ "transformers_version": "4.26.0",
165
  "typical_p": 1.0,
166
  "use_bfloat16": false
167
  },
 
172
  "model_type": "vision-encoder-decoder",
173
  "num_beams": 4,
174
  "pad_token_id": 1,
175
+ "processor_class": "TrOCRProcessor",
176
  "tie_word_embeddings": false,
177
  "torch_dtype": "float32",
178
  "transformers_version": null,
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "length_penalty": 2.0,
8
+ "max_length": 128,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.26.0",
12
+ "use_cache": false
13
+ }
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b4e029f806402a095fd728b480e06fab38d019bfccea95c11ddbb83e80470a1
3
- size 4078814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904d932c3bec61e8398534ed23a126b102c8571c6574aa4295d9efdcdebe4937
3
+ size 4079774
preprocessor_config.json CHANGED
@@ -1,17 +1,22 @@
1
  {
2
  "do_normalize": true,
 
3
  "do_resize": true,
4
- "feature_extractor_type": "ViTFeatureExtractor",
5
  "image_mean": [
6
  0.5,
7
  0.5,
8
  0.5
9
  ],
 
10
  "image_std": [
11
  0.5,
12
  0.5,
13
  0.5
14
  ],
15
  "resample": 2,
16
- "size": 384
 
 
 
 
17
  }
 
1
  {
2
  "do_normalize": true,
3
+ "do_rescale": true,
4
  "do_resize": true,
 
5
  "image_mean": [
6
  0.5,
7
  0.5,
8
  0.5
9
  ],
10
+ "image_processor_type": "ViTImageProcessor",
11
  "image_std": [
12
  0.5,
13
  0.5,
14
  0.5
15
  ],
16
  "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 384,
20
+ "width": 384
21
+ }
22
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02bdabbb33b897784a6b074f1ee3cc3c1a58ee1ebced72b25126b762929f35a
3
  size 1335854221
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a904085b5a8520d5cc39c3a5a87368652fd73eb2b5c50c8179d241949ecf643
3
  size 1335854221
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95b05d5450c9c29c6fd1a956373e8f37871380a13621476c72bb50b5143bb782
3
- size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca297b4574038a4b905ad1628591418f066fd85bb7493f5478155f9ce3004a7
3
+ size 14511
scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca28e537b07b89b3d982116c6f00d83cf311395f81e14ac090680600db56fa99
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a14d9b78036bac3cdd028e5a01265128db09a9d7c722c0dfb51c838ec9211b
3
  size 557
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:519a9af97986ce07be30f1e390d809fa6dc04324d67ee367f177bf4f0f85afa8
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671b0b13ccc248beece7599a7a8283012d3a42ef38a10a6435157b3cff1e55cb
3
  size 627
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9a403686da889b7317126062fe6ef411418cd816c8b90b127deac9c4c070c17
3
- size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb31c6c543c5708bc3887b78f4e385e40d85d55dee8f9640fb094a803ab5ef5
3
+ size 3643