Elastic Transformers
Collection
Hugging Face Transformers models accelerated by TheStage AI ANNA: Automated NNs Accelerator. • 18 items • Updated • 2
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheStageAI/whisper-medium", dtype="auto")Quick Links
Whisper MLX Model
This repository contains a CoreML and MLX-optimized Whisper model for efficient speech recognition on Apple devices.
Model Components
- CoreML encoder for efficient inferencing on Apple Neural Engine
- MLX decoder for fast processing with Apple Silicon optimizations
- HuggingFace Whisper processor and model template
Usage
from asr_streaming import StreamingConfig, StreamingBackend
# Create config with HuggingFace repository
config = StreamingConfig(
use_huggingface=True,
huggingface_repo="TheStageAI/whisper-medium"
)
# Initialize the backend
backend = StreamingBackend(config)
# Now use the backend as normal
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="TheStageAI/whisper-medium")