ternary-models: VLMs, Multimodal & Audio
Collection
Ternary-quantized models for architectures GGUF can't handle. tritplane3 scheme. • 16 items • Updated • 5
Automatic Speech Recognition
Transformers
English
ternary-quant
quantization
ternary
audio
speech-to-text
whisper
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AsadIsmail/whisper-small-ternary", device_map="auto")Quick Links
Whisper-small — Ternary Quantized (tritplane3)
Ternary-quantized version of openai/whisper-small.
Specifications
| Property | Value |
|---|---|
| Parameters | 244M |
| Quantization | tritplane3 (120 decoder layers) |
| Stored size | 127 MB |
| Compression | 1.26× |
Collection
Part of ternary-models.
Model tree for AsadIsmail/whisper-small-ternary
Base model
openai/whisper-small
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="AsadIsmail/whisper-small-ternary")