hhoangphuoc/speechlaugh-wav2vec2

Model Card for Model ID

A Fine-tuned Wav2Vec2 model design for Automatic Recognition Task for Paralinguistic Speech

Model Details

Model Description

This model is create for the ASR task designing for enhance the recognition on paralinguistic speech events (particularly laughter and speech-laugh). The model was intensively train on Switchboard Conversational Speech Corpus, which I have preprocessed for this particular task. You can find more details about this dataset @hhoangphuoc/switchboard

Developed by: @hhoangphuoc

Model Sources [optional]

For more details about the implementation of this model, check out my original Github repository

Repository: https://github.com/hhoangphuoc/SpeechLaughRecogniser

Training Details

Training Hyperparameters

• Training regime: [More Information Needed]

---

Evaluation

---

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• 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]