AuriStream100M_40Pred_BigAudioDataset_500k-randinit
AuriStream is a speech language model by Greta Tuckute and Klemen Kotar.
This model predicts cochlear tokens from a tokenizer such as WavCochCausalV8192.
Native training step-zero initialization for the 100M 40-prediction model. This exactly uses origin seed 11101994 and historical source commit c3ef0ac189b893a321158d6df554eca3148ccd76, matching the start of W&B run 5x3xfsf4. The weights are untrained FP32 values produced before XLA/FSDP wrapping.
Model Details
| Parameter | Value |
|---|---|
| Parameters | ~0.34B |
| Layers | 12 |
| Hidden Size | 768 |
| Attention Heads | 12 |
| Vocab Size | 8192 |
| Prediction Steps | 40 |
Usage
from transformers import AutoModel, AutoConfig
# Load with trust_remote_code for custom model
model = AutoModel.from_pretrained(
"TuKoResearch/AuriStream100M_40Pred_BigAudioDataset_500k-randinit",
trust_remote_code=True,
)
# Or load config first
config = AutoConfig.from_pretrained("TuKoResearch/AuriStream100M_40Pred_BigAudioDataset_500k-randinit", trust_remote_code=True)
Base Model Code
This checkpoint uses shared model code from TuKoResearch/AuriStream-base.
Tokenizer
This model uses cochlear tokens from WavCochCausalV8192.