AI PC: Automatic Speech Recognition
Automatic Speech Recognition models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU.
Automatic Speech Recognition • Updated • 11M • • 299Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSpeechSeq2Seq library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
distil-whisper/distil-medium.en
Automatic Speech Recognition • Updated • 364k • 119Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSpeechSeq2Seq library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
facebook/hubert-large-ls960-ft
Automatic Speech Recognition • Updated • 915k • 59Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForCTC library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
openai/whisper-base
Automatic Speech Recognition • Updated • 894k • 188Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSpeechSeq2Seq library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
openai/whisper-medium
Automatic Speech Recognition • Updated • 1.04M • 212Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSpeechSeq2Seq library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 44.5M • 1.66kNote This model was tested with OpenVINO version 2024.1.0, using the OVModelForSpeechSeq2Seq library with INT8 weight compression to reduce the memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
distil-whisper/distil-large-v3
Automatic Speech Recognition • Updated • 168k • 255Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSpeechSeq2Seq library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
microsoft/unispeech-sat-base-plus-sd
Updated • 297Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForAudioFrameClassification library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
microsoft/unispeech-sat-large-sv
Updated • 272 • 4Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForAudioXVector library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
microsoft/unispeech-sat-base-sv
Updated • 51Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForAudioXVector library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
microsoft/unispeech-1350-en-90-it-ft-1h
Automatic Speech Recognition • Updated • 16Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForCTC library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation