Enhanced meeting summarizer with QMSum dataset

README.md

@@ -0,0 +1,97 @@
+
+---
+language: en
+license: apache-2.0
+tags:
+- text-summarization
+- meeting-summarization
+- t5
+- transformers
+- qmsum
+datasets:
+- qmsum
+metrics:
+- rouge
+pipeline_tag: summarization
+---
+
+# Meeting Summarizer
+
+This model is a fine-tuned version of `t5-small` for meeting summarization tasks.
+
+## Model Details
+- **Base Model**: t5-small
+- **Task**: Abstractive Meeting Summarization
+- **Training Data**: QMSum Dataset + Enhanced Training
+- **Parameters**: t5-small architecture
+
+## Training Configuration
+- **Max Input Length**: 256 tokens
+- **Max Output Length**: 64 tokens
+- **Batch Size**: 16
+- **Learning Rate**: 5e-05
+- **Training Epochs**: 1
+- **Training Samples**: N/A
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("CodeXRyu/meeting-summarizer")
+model = AutoModelForSeq2SeqLM.from_pretrained("CodeXRyu/meeting-summarizer")
+
+def generate_summary(meeting_text, max_length=150):
+    # Prepare input
+    input_text = "summarize: " + meeting_text
+    inputs = tokenizer(input_text, max_length=512, truncation=True, return_tensors="pt")
+    
+    # Generate summary
+    summary_ids = model.generate(
+        inputs["input_ids"],
+        max_length=max_length,
+        num_beams=4,
+        length_penalty=2.0,
+        early_stopping=True
+    )
+    
+    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+# Example usage
+meeting_transcript = '''
+John: Good morning team. Let's discuss our Q3 results.
+Sarah: Our sales exceeded targets by 15%, reaching $2.1M in revenue.
+Mike: The new marketing campaign was very effective.
+John: Great work everyone. Let's plan for Q4.
+'''
+
+summary = generate_summary(meeting_transcript)
+print(summary)
+```
+
+## Training Data
+This model was trained on the QMSum dataset, which contains real meeting transcripts from multiple domains:
+- Academic meetings
+- Product development meetings  
+- Committee meetings
+
+## Performance
+The model achieves competitive ROUGE scores on meeting summarization benchmarks.
+
+## Limitations
+- Optimized for English meeting transcripts
+- Performance may vary on very long meetings (>512 tokens input)
+- Best suited for structured meeting formats with speaker labels
+
+## Citation
+If you use this model, please cite:
+```
+@misc{meeting-summarizer-codexryu,
+  author = {CodeXRyu},
+  title = {Meeting Summarizer},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/CodeXRyu/meeting-summarizer}
+}
+```

checkpoint-13/config.json

@@ -9,6 +9,7 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
+  "dtype": "float32",
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
@@ -53,8 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.3",
+  "transformers_version": "4.56.1",
   "use_cache": true,
   "vocab_size": 32128
 }

checkpoint-13/generation_config.json

@@ -1,7 +1,9 @@
 {
   "_from_model_config": true,
   "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "eos_token_id": [
+    1
+  ],
   "pad_token_id": 0,
-  "transformers_version": "4.53.3"
+  "transformers_version": "4.56.1"
 }

checkpoint-13/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f11c74df923063d7933164164348d9be823169f5aceadd8cb0a28023f1ac33c
+oid sha256:dee695d09e479b8a4c7d50551558815291b54f64c9a0da8779f318595db5c109
 size 242041896

checkpoint-13/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75fb4a23edebce5ed875b14f08369d282ec73aee2ef4eabb12be446a8d91028
+oid sha256:d8780b109dfc27662eb489f645bfc3ad832cc24826668c1a8f9e819f58db915f
 size 484160331

checkpoint-13/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ceacd01edce49487ee660bb5920ae9feaf059c5e1b776cdf398943de0cb848
+oid sha256:2b5761b78333a5edd4121621235e678648f1ce38c9d2b47fab279860f3f0fe5c
 size 14455

checkpoint-13/tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 64,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

checkpoint-13/trainer_state.json

@@ -3,17 +3,25 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.0,
-  "eval_steps": 50,
+  "eval_steps": 20,
   "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
-  "logging_steps": 50,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 4.401995658874512,
+      "learning_rate": 4.5e-05,
+      "loss": 3.8386,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
   "max_steps": 13,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 50,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -26,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 6767090073600.0,
-  "train_batch_size": 8,
+  "total_flos": 13534180147200.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-13/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27571a09d091e90ec5d81bea87b6f6338619054c1522938a6dde9820cca267f4
-size 5841
+oid sha256:a8d2ff0b4552b3f5fe2fa68c6574a4535d4620fe5a9b086dedbf0ccefd6ed20d
+size 5905

config.json

@@ -9,6 +9,7 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
+  "dtype": "float32",
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
@@ -53,8 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.3",
+  "transformers_version": "4.56.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -1,7 +1,8 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "eos_token_id": [
+    1
+  ],
   "pad_token_id": 0,
-  "transformers_version": "4.53.3"
+  "transformers_version": "4.56.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f11c74df923063d7933164164348d9be823169f5aceadd8cb0a28023f1ac33c
+oid sha256:dee695d09e479b8a4c7d50551558815291b54f64c9a0da8779f318595db5c109
 size 242041896

tokenizer.json

@@ -2,18 +2,11 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 64,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27571a09d091e90ec5d81bea87b6f6338619054c1522938a6dde9820cca267f4
-size 5841
+oid sha256:a8d2ff0b4552b3f5fe2fa68c6574a4535d4620fe5a9b086dedbf0ccefd6ed20d
+size 5905

training_config.json

@@ -0,0 +1,11 @@
+{
+  "model_name": "t5-small",
+  "max_input_length": 256,
+  "max_target_length": 64,
+  "batch_size": 16,
+  "learning_rate": 5e-05,
+  "num_epochs": 1,
+  "train_size": 200,
+  "val_size": 40,
+  "test_size": 20
+}