Automatic Speech Recognition
Transformers
ONNX
English
onnxruntime
speech
asr
granite
ibm
quantized
int8
fp16
non-autoregressive
nar
Instructions to use smcleod/ibm-granite-speech-4.1-2b-nar-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use smcleod/ibm-granite-speech-4.1-2b-nar-onnx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="smcleod/ibm-granite-speech-4.1-2b-nar-onnx")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("smcleod/ibm-granite-speech-4.1-2b-nar-onnx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download test_fixtures/sample_audio.wav from smcleod/ibm-granite-speech-4.1-2b-nar-onnx: direct link, hf CLI and curl.
- Browser
- Download file 540 kB
-
https://huggingface.co/smcleod/ibm-granite-speech-4.1-2b-nar-onnx/resolve/main/test_fixtures/sample_audio.wav
- Command line
-
hf download hf://smcleod/ibm-granite-speech-4.1-2b-nar-onnx/test_fixtures/sample_audio.wav
-
curl -L -o sample_audio.wav https://huggingface.co/smcleod/ibm-granite-speech-4.1-2b-nar-onnx/resolve/main/test_fixtures/sample_audio.wav
540 kB
- Xet hash:
- 8f201ee75d113e66753e795dc4a43ae7744709b9b0f848b28564390a901b1920
- Size of remote file:
- 540 kB
- SHA256:
- 6ee3e432f4ce88415747f0549628bfef0df742365813d38b18bf28067a40cd51
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.