Inkling
Thinking Machines Labaudio via discrete token encoding
3 more from this model
audio via discrete token encoding
audio via discrete token encoding
audio via discrete token encoding
specific method · filed under model architecture
Inkling's "discrete token encoding" is dMel: each of 80 mel bins is quantized to one of 16 levels and the 80 embeddings are summed into one token every 50 ms, with no audio encoder or learned codebook.
Written for the explainer Hearing, speaking and keeping time: audio, omni models and multimodal positions.
Also called Discrete token encoding for audio, discrete token encoding, discrete token encoding for audio inputs.
4 quotes from 4 sources, one card per model, each opening with its strongest.
audio via discrete token encoding
audio via discrete token encoding
audio via discrete token encoding
audio via discrete token encoding