Downloads · 30 days
6
12% of all-time downloads
bschooled/caeleste-speech-higgs-audio-v3-stt-nf4
caeleste-speech-higgs-audio-v3-stt-nf4 is a machine learning model from bschooled. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
4-bit NF4 (bitsandbytes) quantization of bosonai/higgs-audio-v3-stt.
Downloads · 30 days
6
12% of all-time downloads
All-time downloads
51
Public
Parameters
2.7B
2.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.8 GB · 99%
How the weights are stored.
U81.7B · 65%
From the Hugging Face model README
4-bit NF4 (bitsandbytes) quantization of
bosonai/higgs-audio-v3-stt.
| Upstream repository | bosonai/higgs-audio-v3-stt |
| Upstream revision | db4966839bef4b0967b43db893631107ebf828b9 |
| Upstream license | apache-2.0 |
| Quantization | bitsandbytes NF4, double quantization, bf16 compute |
| Original size | 5.00 GiB |
| Quantized size | 2.61 GiB |
Speech-to-text (Whisper-large-v3 encoder + Qwen3 decoder).
The weight tensors have been replaced with their NF4-quantized equivalents and a
quantization_config block was added to config.json. Tokenizer, processor,
and any remote-code files are copied unmodified from the upstream revision above.
No architecture, vocabulary, or generation defaults were altered.
Loading requires bitsandbytes and a supported accelerator. NF4 kernels are
available for NVIDIA sm_75+ (Turing and newer) and for AMD ROCm on RDNA3 /
RDNA3.5 / CDNA.
from transformers import AutoModel
model = AutoModel.from_pretrained(
"bschooled/caeleste-speech",
subfolder="higgs-audio-v3-stt-nf4",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
This derivative is distributed under the upstream license, apache-2.0.
All upstream copyright, patent, trademark and attribution notices are retained.
Refer to the upstream repository for the authoritative license text.