YogeLiu/TexTeller
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[chore] exclude paddleocr directory from pre-commit hooks

Browse Source
This commit is contained in:
三洋三洋
2025-02-28 19:56:49 +08:00
parent a8a005ae10
commit 3d546f9993
130 changed files with 592 additions and 739 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
texteller/models/ocr_model/model/TexTeller.py Normal file
View File

@@ -0,0 +1,43 @@
from pathlib import Path
from ...globals import VOCAB_SIZE, FIXED_IMG_SIZE, IMG_CHANNELS, MAX_TOKEN_SIZE
from transformers import RobertaTokenizerFast, VisionEncoderDecoderModel, VisionEncoderDecoderConfig
class TexTeller(VisionEncoderDecoderModel):
REPO_NAME = 'OleehyO/TexTeller'
def __init__(self):
config = VisionEncoderDecoderConfig.from_pretrained(
Path(__file__).resolve().parent / "config.json"
)
config.encoder.image_size = FIXED_IMG_SIZE
config.encoder.num_channels = IMG_CHANNELS
config.decoder.vocab_size = VOCAB_SIZE
config.decoder.max_position_embeddings = MAX_TOKEN_SIZE
super().__init__(config=config)
@classmethod
def from_pretrained(cls, model_path: str = None, use_onnx=False, onnx_provider=None):
if model_path is None or model_path == 'default':
if not use_onnx:
return VisionEncoderDecoderModel.from_pretrained(cls.REPO_NAME)
else:
from optimum.onnxruntime import ORTModelForVision2Seq
use_gpu = True if onnx_provider == 'cuda' else False
return ORTModelForVision2Seq.from_pretrained(
cls.REPO_NAME,
provider="CUDAExecutionProvider" if use_gpu else "CPUExecutionProvider",
)
model_path = Path(model_path).resolve()
return VisionEncoderDecoderModel.from_pretrained(str(model_path))
@classmethod
def get_tokenizer(cls, tokenizer_path: str = None) -> RobertaTokenizerFast:
if tokenizer_path is None or tokenizer_path == 'default':
return RobertaTokenizerFast.from_pretrained(cls.REPO_NAME)
tokenizer_path = Path(tokenizer_path).resolve()
return RobertaTokenizerFast.from_pretrained(str(tokenizer_path))

BIN
texteller/models/ocr_model/model/__pycache__/TexTeller.cpython-310.pyc Normal file
View File

Binary file not shown.

168
texteller/models/ocr_model/model/config.json Normal file
View File

@@ -0,0 +1,168 @@
{
"_name_or_path": "OleehyO/TexTeller",
"architectures": [
"VisionEncoderDecoderModel"
],
"decoder": {
"_name_or_path": "",
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_cross_attention": true,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"classifier_dropout": 0.0,
"cross_attention_hidden_size": 768,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.1,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"init_std": 0.02,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layernorm_embedding": true,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 1024,
"min_length": 0,
"model_type": "trocr",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"scale_embedding": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": false,
"use_learned_position_embeddings": true,
"vocab_size": 15000
},
"encoder": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_probs_dropout_prob": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_stride": 16,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 448,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "vit",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 16,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"qkv_bias": false,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false
},
"is_encoder_decoder": true,
"model_type": "vision-encoder-decoder",
"tie_word_embeddings": false,
"transformers_version": "4.41.2",
"use_cache": true
}