Higgs Audio Tokenizer Check our open source repository https://github.com/boson ai/higgs audio for more details! We introduce a new discretized audio tokenizer that runs at just 25 frames per second while keeping—or even improving—audio quality compared to tokenizers with twice the bitrate. Our model is the first to train on 24 kHz data covering speech, music, and sound events in one unified system. It also uses a simple non diffusion encoder/decoder for fast, batch inference. Usage Transformers 🤗 Higgs Audio V2 Tokenizer is supported natively in transformers : see the doc. Basics of Audio Quantization An audio signal sampled at \\(f s\\) Hz is first split into frames by an encoder with hop size \\(M\\), giving a frame rate \\(f r = \frac{f s}{M}\quad\text{(frames/s)}.\\) Two common quantizers are: Residual Vector Quantization (RVQ) : \\(N q\\) cascaded vector‑quantizer layers, each with codebook size \\(N {cb}\\). When \\(N {q}=1\\), it degenerates to ordinary vector quantization. Finite Scalar Quantization (FSQ) : A single layer scalar quantizer in which every scalar coefficient is independently mapped to one of \\(N {cb}\\) discrete levels. If every combination of codewords is…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy