---
license: other
license_name: adobe-research-license
license_link: https://github.com/adobe-research/speaker-identification/blob/main/LICENSE.md
library_name: pytorch
tags:
  - speaker-identification
  - quantization
  - int8
  - roberta
  - mediasum
---

# Joint SpeakerID INT8 (weight-only)

INT8 weight-only quantisation of the Joint Speaker Identifier from
[adobe-research/speaker-identification](https://github.com/adobe-research/speaker-identification)
([Interspeech 2024](https://arxiv.org/abs/2407.12094)).

**Joint INT8 — 78.87 / 0.00 / 63.28 / 67.60 / 18.34 / 472 MB**

| Metric | Value |
|---|---|
| Precision | **78.87** |
| Δ vs FP32 | **0.00** |
| F1 | 63.28 |
| Accuracy | 67.60 |
| Throughput | 18.34 examples/s (Apple M3 Pro, MPS, batch 2) |
| In-memory size | 472 MB (FP32: 1633 MB) |

Same precision, F1, and accuracy as the FP32 Joint baseline at about 3.5× smaller weights.

Code and eval tables: [HugoMarchant/speaker-identification-quantisation](https://github.com/HugoMarchant/speaker-identification-quantisation).

## Files

- `model.pt` — quantised bundle (`scheme=int8_weight`, group size 64)
- `config.json` — metrics and load metadata

## Load

```python
from huggingface_hub import hf_hub_download
from device_utils import apply_cuda_shims
apply_cuda_shims()
from model_io import load_quantized_bundle

path = hf_hub_download("hmarchant/speaker-id-joint-int8", "model.pt")
model, config, tokenizer, qcfg, info, device = load_quantized_bundle(path)
```

Requires the companion GitHub repo (custom `JointSpeakerIdentifier` + `WeightOnlyQuantizedLinear`).

## License

Derived from Adobe Research Speaker Identification. The
[Adobe Research License](https://github.com/adobe-research/speaker-identification/blob/main/LICENSE.md)
allows **non-commercial research use only**.