metadata

library_name: transformers
tags:
  - wav2vec2
  - automatic-speech-recognition
  - asr
  - audio
  - speech
  - pytorch
  - opensource
license: apache-2.0
language:
  - en
base_model:
  - facebook/wav2vec2-base
pipeline_tag: automatic-speech-recognition

Model Card for Wav2Vec2-Tellmate

Wav2Vec2-Tellmate is a speech recognition model, fine-tuned for chess coordinates.

Model Details

wav2vec2-tellmate was trained on nearly 2,500 chess coordinate audio files (in english), to ensure fast and reliable chess coordinate recognition. Note: It is not been trained on chess moves (yet) nor other chess terminology. Just the coordinates themselves.

Developed by: Leonardo Palomino
Model type: Automatic Speech Recognition (ASR)
Language(s) (NLP): English
License: Apache license 2.0
Finetuned from model: facebook/wav2-vec-2-base (https://huggingface.co/facebook/wav2vec2-base)