Task
Automatic Speech Recognition
G
ibm-granite/granite-speech-3.3-8b
Automatic Speech Recognition·ibm-granite· 182.2K· 171
transformers
apache-2.0
Automatic Speech Recognition
8.6B params
arxiv:2505.08699base_model:ibm-granite/granite-3.3-8b-instruct
Model Summary: Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST). Granite-speech-3.3-8b uses a two-pass design, unlike integrated models that combine speech and language into a single pass. Initial calls to granite-speech-3.3-8b will transcribe audio files into text. To process
# pull & run locally
pip install mlforge-sdk && mlforge pull ibm-granite/granite-speech-3.3-8b
pip install mlforge-sdk && mlforge pull ibm-granite/granite-speech-3.3-8b
Model details
Provider
ibm-granite
Framework
transformers
Parameters
8.6B
Size
19 GB
License
apache-2.0
Downloads
182.2K
Likes
171
Paper
arXiv:2505.08699
Updated
2026-04-02
About ibm-granite/granite-speech-3.3-8b
Model Summary: Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST). Granite-speech-3.3-8b uses a two-pass design, unlike integrated models that combine speech and language into a single pass. Initial calls to granite-speech-3.3-8b will transcribe audio files into text. To process the transcribed text using the underlying Granite language model, users must make a second call as each step must be explicitly initiated.