Update config.json

config.json

@@ -1,166 +1,63 @@
-{
-  "model_name": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
-  "num_labels": 9,
-  "aphasia_types_mapping": {
-    "BROCA": 0,
-    "TRANSMOTOR": 1,
-    "NOTAPHASICBYWAB": 2,
-    "CONDUCTION": 3,
-    "WERNICKE": 4,
-    "ANOMIC": 5,
-    "GLOBAL": 6,
-    "ISOLATION": 7,
-    "TRANSSENSORY": 8
-  },
-  "training_args": {
-    "output_dir": "./adaptive_aphasia_model",
-    "overwrite_output_dir": false,
-    "do_train": false,
-    "do_eval": true,
-    "do_predict": false,
-    "eval_strategy": "epoch",
-    "prediction_loss_only": false,
-    "per_device_train_batch_size": 10,
-    "per_device_eval_batch_size": 10,
-    "per_gpu_train_batch_size": null,
-    "per_gpu_eval_batch_size": null,
-    "gradient_accumulation_steps": 4,
-    "eval_accumulation_steps": null,
-    "eval_delay": 0,
-    "torch_empty_cache_steps": null,
-    "learning_rate": 0.0005,
-    "weight_decay": 0.01,
-    "adam_beta1": 0.9,
-    "adam_beta2": 0.999,
-    "adam_epsilon": 1e-08,
-    "max_grad_norm": 1.0,
-    "num_train_epochs": 500,
-    "max_steps": -1,
-    "lr_scheduler_type": "linear",
-    "lr_scheduler_kwargs": {},
-    "warmup_ratio": 0.1,
-    "warmup_steps": 0,
-    "log_level": "passive",
-    "log_level_replica": "warning",
-    "log_on_each_node": true,
-    "logging_dir": "./adaptive_aphasia_model/runs/Aug06_00-31-47_ikm-gpu-9104",
-    "logging_strategy": "steps",
-    "logging_first_step": false,
-    "logging_steps": 50,
-    "logging_nan_inf_filter": true,
-    "save_strategy": "epoch",
-    "save_steps": 500,
-    "save_total_limit": 3,
-    "save_safetensors": true,
-    "save_on_each_node": false,
-    "save_only_model": false,
-    "restore_callback_states_from_checkpoint": false,
-    "no_cuda": false,
-    "use_cpu": false,
-    "use_mps_device": false,
-    "seed": 42,
-    "data_seed": null,
-    "jit_mode_eval": false,
-    "use_ipex": false,
-    "bf16": false,
-    "fp16": false,
-    "fp16_opt_level": "O1",
-    "half_precision_backend": "auto",
-    "bf16_full_eval": false,
-    "fp16_full_eval": false,
-    "tf32": null,
-    "local_rank": 1,
-    "ddp_backend": null,
-    "tpu_num_cores": null,
-    "tpu_metrics_debug": false,
-    "debug": [],
-    "dataloader_drop_last": true,
-    "eval_steps": null,
-    "dataloader_num_workers": 0,
-    "dataloader_prefetch_factor": null,
-    "past_index": -1,
-    "run_name": "./adaptive_aphasia_model",
-    "disable_tqdm": false,
-    "remove_unused_columns": false,
-    "label_names": null,
-    "load_best_model_at_end": true,
-    "metric_for_best_model": "eval_f1",
-    "greater_is_better": true,
-    "ignore_data_skip": false,
-    "fsdp": [],
-    "fsdp_min_num_params": 0,
-    "fsdp_config": {
-      "min_num_params": 0,
-      "xla": false,
-      "xla_fsdp_v2": false,
-      "xla_fsdp_grad_ckpt": false
-    },
-    "fsdp_transformer_layer_cls_to_wrap": null,
-    "accelerator_config": {
-      "split_batches": false,
-      "dispatch_batches": null,
-      "even_batches": true,
-      "use_seedable_sampler": true,
-      "non_blocking": false,
-      "gradient_accumulation_kwargs": null
-    },
-    "deepspeed": null,
-    "label_smoothing_factor": 0.0,
-    "optim": "adamw_torch",
-    "optim_args": null,
-    "adafactor": false,
-    "group_by_length": false,
-    "length_column_name": "length",
-    "report_to": [],
-    "ddp_find_unused_parameters": null,
-    "ddp_bucket_cap_mb": null,
-    "ddp_broadcast_buffers": null,
-    "dataloader_pin_memory": true,
-    "dataloader_persistent_workers": false,
-    "skip_memory_metrics": true,
-    "use_legacy_prediction_loop": false,
-    "push_to_hub": false,
-    "resume_from_checkpoint": null,
-    "hub_model_id": null,
-    "hub_strategy": "every_save",
-    "hub_token": "<HUB_TOKEN>",
-    "hub_private_repo": null,
-    "hub_always_push": false,
-    "gradient_checkpointing": false,
-    "gradient_checkpointing_kwargs": null,
-    "include_inputs_for_metrics": false,
-    "include_for_metrics": [],
-    "eval_do_concat_batches": true,
-    "fp16_backend": "auto",
-    "push_to_hub_model_id": null,
-    "push_to_hub_organization": null,
-    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
-    "mp_parameters": "",
-    "auto_find_batch_size": false,
-    "full_determinism": false,
-    "torchdynamo": null,
-    "ray_scope": "last",
-    "ddp_timeout": 1800,
-    "torch_compile": false,
-    "torch_compile_backend": null,
-    "torch_compile_mode": null,
-    "include_tokens_per_second": false,
-    "include_num_input_tokens_seen": false,
-    "neftune_noise_alpha": null,
-    "optim_target_modules": null,
-    "batch_eval_metrics": false,
-    "eval_on_start": false,
-    "use_liger_kernel": false,
-    "eval_use_gather_object": false,
-    "average_tokens_across_devices": false
-  },
-  "adaptive_lr_config": {
-    "adaptive_lr": true,
-    "lr_patience": 3,
-    "lr_factor": 0.8,
-    "lr_increase_factor": 1.2,
-    "min_lr": 1e-06,
-    "max_lr": 0.001,
-    "oscillation_amplitude": 0.1
-  }
-}
+---
+title: Aphasia Classifier
+emoji: 🧠
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: "4.44.0"
+app_file: app.py
+pinned: false
+license: mit
+short_description: AI-powered aphasia severity classification using fine-tuned BioBERT
+tags:
+- medical
+- nlp
+- aphasia
+- biobert
+- classification
+- speech-therapy
+- healthcare
+models:
+- dmis-lab/biobert-base-cased-v1.1
+---
+
+# Aphasia Classifier 🧠
+
+An AI-powered application for classifying aphasia severity levels using a fine-tuned BioBERT model.
+
+## Features
+
+- **Speech Analysis Pipeline**: Text → CHA Format → JSON → BioBERT Classification
+- **Severity Classification**: Normal, Mild, Moderate, Severe aphasia levels
+- **Confidence Scoring**: Detailed probability distributions for each class
+- **Professional Interface**: Medical-grade UI with multiple output views
+- **Real-time Processing**: Complete analysis in seconds
+
+## How to Use
+
+1. Enter a speech sample in the text area
+2. Click "Analyze Speech" to process through the pipeline
+3. View results across multiple tabs:
+   - **Results**: Formatted analysis with confidence scores
+   - **CHA Format**: Clinical CHAT format output
+   - **JSON Data**: Structured data representation
+   - **Raw Classification**: Complete model output
+
+## Model Information
+
+- **Base Model**: BioBERT (dmis-lab/biobert-base-cased-v1.1)
+- **Fine-tuning**: Specialized for aphasia severity classification
+- **Input**: Natural language speech samples
+- **Output**: 4-class severity classification with confidence scores
+
+## Disclaimer
+
+⚠️ This tool is for research and educational purposes only. It should not be used as a substitute for professional medical diagnosis or treatment. Always consult with qualified healthcare professionals for medical advice.
+
+## Technical Pipeline
+
+```
+Text Input → CHA Formatting → JSON Structure → BioBERT Model → Classification Results
+```
+
+Built with Gradio and Transformers library.