Update README.md

README.md

@@ -1,202 +1,79 @@
 ---
-base_model: google/flan-t5-base
+language:
+- en
+tags:
+- text2text-generation
+license: mit
+datasets:
+- PeacefulData/HyPoradise-v0
 library_name: peft
+pipeline_tag: text2text-generation
+widget:
+  - text: "Generate the correct transcription for the following n-best list of ASR hypotheses: \n\n1. nebode also typically is symphons and an ankle surf leash \n2. neboda is also typically is symphons and an ankle surf leash \n3. nebode also typically is swim fins and an ankle surf leash \n4. neboda also typically is symphons and an ankle surf leash \n5. neboda is also typically is swim fins and an ankle surf leash"
+base_model:
+- google/flan-t5-base
 ---
 
-# Model Card for Model ID
+# FLANEC: Exploring FLAN-T5 for Post-ASR Error Correction
 
-<!-- Provide a quick summary of what the model is/does. -->
+## Model Overview
 
+FLANEC is an encoder-decoder model based on FLAN-T5, specifically fine-tuned for post-Automatic Speech Recognition (ASR) error correction, also known as Generative Speech Error Correction (GenSEC). The model utilizes n-best hypotheses from ASR systems to enhance the accuracy and grammaticality of final transcriptions by generating a single corrected output. FLANEC models are trained on diverse subsets of the [HyPoradise dataset](https://huggingface.co/datasets/PeacefulData/HyPoradise-v0), leveraging multiple ASR domains to provide robust, scalable error correction across different types of audio data.
 
+FLANEC was developed for the **GenSEC Task 1 challenge at SLT 2024** - [Challenge website](https://sites.google.com/view/gensec-challenge/home).
 
-## Model Details
+## Model Checkpoints
 
-### Model Description
+**Cumulative Dataset (CD) Models trained with full fine-tuning:**
 
-<!-- Provide a longer summary of what this model is. -->
+- [FLANEC Base CD](https://huggingface.co/morenolq/flanec-base-cd): Base model with ~250 million parameters, fine-tuned for post-ASR correction on cumulative datasets.
+- [FLANEC Large CD](https://huggingface.co/morenolq/flanec-large-cd): Large model with ~800 million parameters, fine-tuned for post-ASR correction on cumulative datasets.
+- [FLANEC XL CD](https://huggingface.co/morenolq/flanec-xl-cd): Extra-large model with ~3 billion parameters, fine-tuned for post-ASR correction on cumulative datasets.
 
+**Cumulative Dataset (CD) Models trained with Low-Rank Adaptation (LoRA):**
 
+- [FLANEC Base LoRA](https://huggingface.co/morenolq/flanec-base-cd-lora): Base model with ~250 million parameters, fine-tuned with LoRA on cumulative datasets.
+- [FLANEC Large LoRA](https://huggingface.co/morenolq/flanec-large-cd-lora): Large model with ~800 million parameters, fine-tuned with LoRA on cumulative datasets.
+- [FLANEC XL LoRA](https://huggingface.co/morenolq/flanec-xl-cd-lora): Extra-large model with ~3 billion parameters, fine-tuned with LoRA on cumulative datasets.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+## Intended Use
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
+FLANEC is designed for the task of Generative Speech Error Correction (GenSEC). The model is suitable for post-processing ASR outputs to correct grammatical and linguistic errors. The model supports the **English** language.
 
 ## Training Details
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
+### Datasets
 
-## Glossary [optional]
+FLANEC is trained on the [HyPoradise dataset](https://huggingface.co/datasets/PeacefulData/HyPoradise-v0), which contains data from eight ASR domains:
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+1. **WSJ**: Business and financial news.
+2. **ATIS**: Airline travel queries.
+3. **CHiME-4**: Noisy speech.
+4. **Tedlium-3**: TED talks.
+5. **CV-accent**: Accented speech.
+6. **SwitchBoard**: Conversational speech.
+7. **LRS2**: BBC program audio.
+8. **CORAAL**: Accented speech from African American English.
 
-[More Information Needed]
+For more details, see the [HyPoradise paper](https://proceedings.neurips.cc/paper_files/paper/2023/hash/6492267465a7ac507be1f9fd1174e78d-Abstract-Datasets_and_Benchmarks.html).
 
-## More Information [optional]
+### Training Strategy
 
-[More Information Needed]
+The model has been fine-tuned using both full fine-tuning and LoRA (Low-Rank Adaptation) methods. Fine-tuning was performed on multiple model scales, ranging from 250M to 3B parameters. Both single-dataset (SD) and cumulative dataset (CD) training approaches were employed to assess model performance across different ASR domains.
 
-## Model Card Authors [optional]
+For more information on the training strategy, refer to the SLT 2024 paper.
 
-[More Information Needed]
+## Citation
 
-## Model Card Contact
+Please use the following citation to reference this work in your research:
 
-[More Information Needed]
-### Framework versions
+**citation will be updated soon after SLT 2024 proceedings are published**
 
-- PEFT 0.11.1
+```bibtex
+@inproceedings{moreno2024flanec,
+  title={FLANEC: Exploring FLAN-T5 for Post-ASR Error Correction},
+  author={La Quatra, Moreno and Salerno, Valerio and Tsao, Yu and Sabato Marco, Siniscalchi},
+  booktitle={Proceedings of the 2024 IEEE Workshop on Spoken Language Technology},
+  year={2024}
+}
+```