Instructions to use ibm-granite/granite-speech-5.0-470m-turboctc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-5.0-470m-turboctc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-5.0-470m-turboctc")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("ibm-granite/granite-speech-5.0-470m-turboctc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download assets/conformer_blocks.png from ibm-granite/granite-speech-5.0-470m-turboctc: direct link, hf CLI and curl.
- Browser
- Download file 154 kB
-
https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc/resolve/main/assets/conformer_blocks.png
- Command line
-
hf download hf://ibm-granite/granite-speech-5.0-470m-turboctc/assets/conformer_blocks.png
-
curl -L -o conformer_blocks.png https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc/resolve/main/assets/conformer_blocks.png
154 kB

- Xet hash:
- 2bfb1c39f48cc2bd276a67c03f8e5ed77a398071dbcfb34730f877e47b4da759
- Size of remote file:
- 154 kB
- SHA256:
- 297e132365ad251b61de5ebcc69b5c98e5ab735b065ec70364d52c416d43cead
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.