Model Card for Model ID

This is a wav2vec2 model, finetuned for pause-aware ASR and turn-taking prediction. For more details, see our technical report.

Inference should be same as any other wav2vec2 model, just with turn-taking tokens.

Downloads last month: 16

Safetensors

Model size

94.4M params

Tensor type

F32

Inference Examples

Automatic Speech Recognition

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tincans-ai/pause-asr-alpha

Base model

facebook/wav2vec2-base-960h

Finetuned

(119)

this model