README.md

---
library_name: transformers
license: other
license_name: mit-apache-2.0-and-bsd-3-clause
license_link: LICENSE
pipeline_tag: feature-extraction
tags:
- audio
- resemblyzer
- speaker-embedding
- speaker-verification
---

# Resemblyzer

[`resemble-ai/Resemblyzer`](https://github.com/resemble-ai/Resemblyzer), adapted to use with only `torch`, `torchaudio`, and `transformers`.

```python
import soundfile as sf
import torch
from transformers import AutoModel

device = "cuda" if torch.cuda.is_available() else "cpu"
wav, sr = sf.read("audio.wav", dtype="float32")
wav = torch.from_numpy(wav)
model = AutoModel.from_pretrained(
    "prj-beatrice/resemblyzer-torch-native", trust_remote_code=True
).eval().to(device)

with torch.inference_mode():
    embedding = model(wav.to(device), sampling_rate=sr).embeddings[0]
```

The result matches this code:

```python
from resemblyzer import VoiceEncoder, preprocess_wav

# Non-16 kHz input is resampled differently, so exact agreement is not expected.
assert sr == 16_000
reference = torch.from_numpy(
    VoiceEncoder().embed_utterance(preprocess_wav("audio.wav"))
)
torch.testing.assert_close(embedding.cpu(), reference)
```

Padded batches use a waveform tensor `[batch_size, max_length]` and an `input_lengths` tensor `[batch_size]`.

## License

Resemblyzer components are Apache-2.0, WebRTC VAD components are BSD-3-Clause, and the wrapper is MIT-licensed; see `LICENSE`.