Instructions to use ibm-granite/granite-speech-4.1-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-4.1-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-4.1-2b")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ibm-granite/granite-speech-4.1-2b") model = AutoModelForMultimodalLM.from_pretrained("ibm-granite/granite-speech-4.1-2b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: mean_wer | |
| value: 5.33 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: rtfx | |
| value: 231.29 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: ami_wer | |
| value: 8.09 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: earnings22_wer | |
| value: 8.37 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: gigaspeech_wer | |
| value: 9.80 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: librispeech_clean_wer | |
| value: 1.33 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: librispeech_other_wer | |
| value: 2.50 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: spgispeech_wer | |
| value: 3.78 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: tedlium_wer | |
| value: 3.07 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: voxpopuli_wer | |
| value: 5.70 | |
| date: '2026-04-23' | |
| source: | |
| url: https://huggingface.co/ibm-granite/granite-speech-4.1-2b # in .eval_results/ | |