| --- |
| language: |
| - en |
| tags: |
| - Voice |
| datasets: |
| - JBJoyce/DENTAL_CLICK |
| metrics: |
| - accuracy |
| --- |
| |
| ### Model Description |
| Model utilizes Wav2vec2 architecture trained on the Superb dataset for keyword spotting task and was fine |
| tuned to identify dental dental click utterance (https://en.wikipedia.org/wiki/Dental_click) in speech. |
| Model was trained for 10 epochs on a limited quantity of speech (~1.5 hours) and with only one speaker. |
| Thus the model should not be assumed to hold generalizability to other speakers or languages without further |
| training data or rigorous testing. |
| |
| Model was evaluated for accuracy on a hold out test set of 20% of the available data and scored 97%. |
| |
| ## Uses |
| Model can be used via transformers library or via Hugging Face Hosted inference API to the right. I would |
| caution against the use of the 'Record from browser' option as model may erronously identify user's mouse |
| click as a speech utterance. Audio files for upload should be 1 sec in length, with 'WAV' format and 16 bit |
| signed integer PCM encoding. |
