aahouzi/whisper-npu

By aahouzi · ↓ 0 · ♥ 1 · Updated 2025-02-28

What's in this repo

This page lists the files in aahouzi/whisper-npu, including silero_vad.onnx.

1 ONNX models (.onnx files)
48 files, including 26 .dll, 10 .bin, 8 .xml, 1 .md, 1 .onnx, 1 .exe
Last updated 2025-02-28

ONNX files

File	Size	Download
models/VAD/silero-vad/silero_vad.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Whisper-medium OpenVINO IR

Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.

Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al from OpenAI. The original code repository can be found here.

Disclaimer: Content for this model card has partly been copied and pasted from this model card.

Model details

Whisper is a Transformer based encoder-decoder model, also referred to as a sequence-to-sequence model.

Pipeline Image

Model Type	Parameters	n_audio_ctx	n_audio_state	n_audio_head	n_audio_layer	n_text_ctx	n_text_state	n_text_head	n_text_layer	n_mels	n_vocab
whisper-tiny	39 M	1500	384	6	4	224	384	6	4	80	51865
whisper-base	74 M	1500	512	8	6	224	512	8	6	80	51865
whisper-small	244 M	1500	768	12	12	224	768	12	12	80	51865
whisper-medium	769 M	1500	1024	16	24	224	1024	16	16	80	51865
whisper-large-v1	1550 M	1500	1280	20	32	224	1280	20	20	80	51865
whisper-large-v2	1550 M	1500	1280	20	32	224	1280	20	20	80	51865
distil-whisper-large-v2	756 M	1500	1280	20	32	224	1280	20	2	80	51865
whisper-large-v3	1550 M	1500	1280	20	32	224	1280	20	20	128	51866
distil-whisper-large-v3	756 M	1500	1280	20	32	224	1280	20	2	128	51866
whisper-large-v3-turbo	809 M	1500	1280	20	32	224	1280	20	4	128	51866

Model info

automatic-speech-recognition

onnx audio automatic-speech-recognition en zh de es ru ko fr ja pt

↓ 0 ♥ 1

Created: 2025-02-27

Updated: 2025-02-28

View on Hugging Face

Files (48)

.gitattributes

README.md

SDL2.dll

core_tokenizers.dll

icudt70.dll

icuuc70.dll

models/VAD/pyannote-vad/vad.bin

models/VAD/pyannote-vad/vad.xml

models/VAD/silero-vad/silero_vad.onnx ONNX

models/mel_filters_data_128.bin

models/mel_filters_data_80.bin

models/tokenizer/openvino_detokenizer.bin

models/tokenizer/openvino_detokenizer.xml

models/tokenizer/openvino_detokenizer_largev3.bin

models/tokenizer/openvino_detokenizer_largev3.xml

models/tokenizer/openvino_tokenizer.bin

models/tokenizer/openvino_tokenizer.xml

models/tokenizer/openvino_tokenizer_largev3.bin

models/tokenizer/openvino_tokenizer_largev3.xml

models/whisper_medium/whisper_medium_decoder_static_kvcache_224_lm_QKs.bin

models/whisper_medium/whisper_medium_decoder_static_kvcache_224_lm_QKs.xml

models/whisper_medium/whisper_medium_encoder.bin

models/whisper_medium/whisper_medium_encoder.xml

models/whisper_medium/whisper_medium_encoder_decoder_cross_kv.bin

models/whisper_medium/whisper_medium_encoder_decoder_cross_kv.xml

onnxruntime.dll

onnxruntime_providers_shared.dll

openvino.dll

openvino_auto_batch_plugin.dll

openvino_auto_plugin.dll

openvino_c.dll

openvino_hetero_plugin.dll

openvino_intel_cpu_plugin.dll

openvino_intel_gpu_plugin.dll

openvino_intel_npu_plugin.dll

openvino_ir_frontend.dll

openvino_onnx_frontend.dll

openvino_paddle_frontend.dll

openvino_pytorch_frontend.dll

openvino_tensorflow_frontend.dll

openvino_tensorflow_lite_frontend.dll

openvino_tokenizers.dll

samplerate.dll

tbb12.dll

tbbbind_2_5.dll

tbbmalloc.dll

tbbmalloc_proxy.dll

whisper.exe

Related models

More from aahouzi

No other models by this author.

More automatic-speech-recognition models

Browse all automatic-speech-recognition models