IPLC T5 Clinical Report Generator

This is a fine-tuned T5 model specialized in generating clinical report summaries for speech-language pathology evaluations. The model has been trained on a custom dataset of clinical reports and evaluation forms.

Model Description

  • Model Type: T5 (Text-to-Text Transfer Transformer)
  • Base Model: t5-small
  • Task: Clinical Report Summarization
  • Domain: Speech-Language Pathology
  • Language: English

Intended Use

This model is designed to assist speech-language pathologists in generating clinical report summaries from structured evaluation data. It can process information about:

  • Patient demographics
  • Diagnostic information
  • Language assessments
  • Clinical observations
  • Evaluation results

Training Data

The model was fine-tuned on a custom dataset of speech-language pathology evaluation reports and clinical documentation.

Usage

from transformers import T5ForConditionalGeneration, T5Tokenizer

model = T5ForConditionalGeneration.from_pretrained("pdarleyjr/iplc-t5-model")
tokenizer = T5Tokenizer.from_pretrained("pdarleyjr/iplc-t5-model")

text = "summarize: evaluation type: initial. primary diagnosis: F84.0. severity: mild. primary language: english"
input_ids = tokenizer.encode(text, return_tensors="pt", max_length=512, truncation=True)

outputs = model.generate(
    input_ids,
    max_length=256,
    num_beams=4,
    no_repeat_ngram_size=3,
    length_penalty=2.0,
    early_stopping=True
)

summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(summary)

Limitations

  • The model is specifically trained for speech-language pathology evaluations
  • Input should follow the expected format for optimal results
  • Clinical judgment should always be used to verify generated summaries
Downloads last month
17
Safetensors
Model size
248M params
Tensor type
F32
ยท
Inference Providers NEW
Examples

Space using pdarleyjr/iplc-t5-model 1