Instructions to use FastFlowLM/Whisper-V3-Turbo-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FastFlowLM/Whisper-V3-Turbo-NPU2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="FastFlowLM/Whisper-V3-Turbo-NPU2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("FastFlowLM/Whisper-V3-Turbo-NPU2") model = AutoModelForSpeechSeq2Seq.from_pretrained("FastFlowLM/Whisper-V3-Turbo-NPU2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download encoder_dequant.xclbin from FastFlowLM/Whisper-V3-Turbo-NPU2: direct link, hf CLI and curl.
- Browser
- Download file 115 kB
-
https://huggingface.co/FastFlowLM/Whisper-V3-Turbo-NPU2/resolve/main/encoder_dequant.xclbin
- Command line
-
hf download hf://FastFlowLM/Whisper-V3-Turbo-NPU2/encoder_dequant.xclbin
-
curl -L -o encoder_dequant.xclbin https://huggingface.co/FastFlowLM/Whisper-V3-Turbo-NPU2/resolve/main/encoder_dequant.xclbin
115 kB
- Xet hash:
- db55cbd24f6b94afe2bcc784f2e7a5663474a0ac27038c703d9dc49317caf944
- Size of remote file:
- 115 kB
- SHA256:
- e9bfd2ee346dbdcd074aaf595e86b2f8e7505bb383276506ed6a1e0280f2cb6a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.