Downloads · 30 days
5
33% of all-time downloads
tiagoCuervo/lf2ar-speech-2b
lf2ar-speech-2b is a machine learning model from tiagoCuervo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for interleaved-lm. The card lists the license as apache-2.0.
Speech LF²AR checkpoint from LF²AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models. This model has 1,980,911,664 parameters and uses dynamic attention residuals.
Downloads · 30 days
5
33% of all-time downloads
All-time downloads
15
Public
Parameters
2B
7.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.9 GB · 100%
From the Hugging Face model README
Speech LF²AR checkpoint from LF²AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models. This model has 1,980,911,664 parameters and uses dynamic attention residuals.
from interleaved_lm import PerceptionExpressionAdaptedTextLM
from interleaved_lm.audio import generate_speech
model = PerceptionExpressionAdaptedTextLM.from_pretrained(
"tiagoCuervo/lf2ar-speech-2b", device="cuda"
)
codes = generate_speech(model, "A short story about the moon", max_new_tokens=250)
Speech is represented by consecutive-run-collapsed 25 Hz mHuBERT layer-11 K-means units (K=500; EOS=500; PAD=501). A vocoder is not bundled.
The text backbone is initialized from SmolLM. Speech-tokenizer and vocoder artifacts are credited in the Interleaved-LM third-party notices.
| Task | Direction | Accuracy |
|---|---|---|
| sstorycloze | audio-audio | 61.57 |
| sstorycloze | text-text | 73.70 |
| sstorycloze | audio-text | 63.98 |
| sstorycloze | text-audio | 64.03 |
| tstorycloze | audio-audio | 87.60 |
| tstorycloze | text-text | 92.52 |
| tstorycloze | audio-text | 86.91 |
| tstorycloze | text-audio | 83.97 |
See provenance.json for exact hashes and evaluation metadata.