---
library_name: speechbrain
tags:
  - hybridcodec
  - speech
  - audio
  - codec
  - speechbrain
---

# hybridcodec_scratch_50hz

HybridCodec is a speech codec that represents audio with a discrete semantic
stream and a continuous residual stream. This repository contains the
**Scratch** quantizer configuration, operating at a semantic token rate of
**50 Hz**. The codec uses the pretrained FocalCodec 50 Hz encoder and
vocoder with the matching HybridCodec quantizer weights.

## Intended use

Encode mono speech audio into HybridCodec semantic and residual streams, and
decode those streams back into audio. The model configuration expects audio at
16 kHz. Use the same repository for encoding and decoding.

## Files

- `hyperparams.yaml`: model architecture and inference configuration.
- `weights/`: quantizer parameters in safetensors format.

## Install

Install HybridCodec from GitHub:

```bash
pip install "git+https://github.com/hybridcodec/hybridcodec.git"
```

## Encode and decode audio

Load this model from the Hugging Face Hub, encode a WAV file, and write the
reconstruction:

```python
import soundfile as sf
import torch
from hybridcodec.inference import HybridCodec

codec = HybridCodec.from_hparams(source="hybridcodec/hybridcodec_scratch_50hz")
waveform = codec.load_audio("sample.wav").squeeze(-1).to(codec.device)
lengths = torch.ones(1, device=codec.device)
semantic, residual = codec.encode(waveform.unsqueeze(0), lengths)
reconstruction = codec.decode(semantic, residual)
sf.write("reconstructed.wav", reconstruction[0].cpu().numpy(), 16000)
```
## Paper

See [HybridCodec: Modeling Discrete and Continuous Representations for
Efficient Speech Language Models](https://arxiv.org/abs/2606.27627).