klemenk's picture
Upload AuriStream Parallel checkpoint
567be61 verified
---
license: apache-2.0
tags:
- audio
- speech
- language-model
- auristream
- discrete-diffusion
library_name: transformers
---
# AuriStreamParallel100M_Group16_BigAudioDataset_150k
**AuriStream Parallel** is a discrete diffusion speech language model by **Greta Tuckute** and **Klemen Kotar**.
## Model Details
| Parameter | Value |
|-----------|-------|
| Parameters | ~0.20B |
| Layers | 12 |
| Hidden Size | 768 |
| Attention Heads | 12 |
| Vocab Size | 8193 |
| Group Size | 16 |
| Mask Schedule | linear_text_prime |
## Architecture
- Bidirectional transformer attention
- Grouped token latent projection
- Parallel token heads for group-wise prediction
- Partial masking diffusion objective
## Usage
```python
from transformers import AutoModel
model = AutoModel.from_pretrained(
"TuKoResearch/AuriStreamParallel100M_Group16_BigAudioDataset_150k",
trust_remote_code=True,
)
```
## Base Model Code
This checkpoint uses shared model code from [TuKoResearch/AuriStreamParallel-base](https://huggingface.co/TuKoResearch/AuriStreamParallel-base).
## Tokenizer
This model is intended for cochlear tokens, e.g. from [WavCochCausalV8192](https://huggingface.co/TuKoResearch/WavCochCausalV8192).