OLMoASR

--- license: apache-2.0 pipeline_tag: audio-text-to-text --- # OLMoASR OLMoASR is a series of English automatic speech recognition (ASR) models proposed in the [OLMoASR: Open Models and Data for Training Robust Speech Recognition Models](https://github.com/allenai/OLMoASR.git) paper by Huong Ngo et al. from Ai2. Trained on 440K hours of weakly-supervised audio-text pairs collected from the public internet, OLMoASR demonstrates strong robustness and zero-shot capabilities. Visit the [OLMoASR repository](https://github.com/allenai/OLMoASR.git) for access to data processing, training and evaluation code. # Model Details OLMoASR uses a Transformer-based encoder-decoder architecture and is an audio language model (LM), where there is an audio encoder and language decoder. OLMoASR has 5 different model sizes and all checkpoints are trained with English-only data. Below is a table enumerating the different model sizes and associated parameter count. | Size | Parameters | |-----------|------------| | tiny | 39 M | | base | 74 M | | small | 244 M | | medium | 769 M | | large | 1.5 B | | large-v2 | 1.5 B | # Training Data OLMoASR is trained on 440K hours of weakly-supervised data subsampled from OLMoASR-Mix, a filtered version of [OLMoASR-Pool](link). OLMoASR-Mix is a collection 1M hours of audio-text pairs, curated from the 3M hours of OLMoASR-Pool. # Usage To perform transcription, you can run ``` import olmoasr model = olmoasr.load_model("medium", inference=True) result = model.transcribe("audio.mp3") print(result) ``` # Evaluation To perform evaluation, you can visit the [OLMoASR repository](https://github.com/allenai/OLMoASR.git) for more details. # License This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with [Ai2's Responsible Use Guidelines](https://allenai.org/responsible-use). # BibTeX entry and citation info ``` @misc{ngo2025olmoasropenmodelsdata, title={OLMoASR: Open Models and Data for Training Robust Speech Recognition Models}, author={Huong Ngo and Matt Deitke and Martijn Bartelds and Sarah Pratt and Josh Gardner and Matt Jordan and Ludwig Schmidt}, year={2025}, eprint={2508.20869}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2508.20869}, } ```

Source context: 3 downloads · 79 likes · Pipeline audio-text-to-text · Repo allenai/OLMoASR

Source context: 0 downloads · 79 likes · Pipeline audio-text-to-text · Repo allenai/OLMoASR