Aller au contenu

ModelVérifiéExterne

Whisperkit Coreml

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon:

Sourcehuggingface.co/argmaxinc/whisperkit-coreml/tree/0f63a7800b00dd0226abd051b906c246e1907482

TypeOtherVersionRevision 0f63a78Éditeur@argmaxincBClasse

Source du modèle

Type: Other
Taille du fichier: 243 B–1,19 GB
Version: vRevision 0f63a78
Mis à jour: 4 oct. 2026
Éditeur: @argmaxinc
Téléchargements: 10,7 M
Source: Hugging Face

Description de la source

WhisperKit

Repo

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift

Paper

Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854

Pro

For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Sources

1 source

Hugging FacePrincipalVersion 0f63a7800b00dd0226abd051b906c246e1907482

huggingface.co/argmaxinc/whisperkit-coreml/tree/0f63a7800b00dd0226abd051b906c246e1907482

Vérifié 4 oct.

Artefacts du modèle

64 artefacts

distil-whisper_distil-large-v3_594MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 79120bd7c421…f2ac · Hugging Face

distil-whisper_distil-large-v3_594MB/AudioEncoder.mlmodelc/coremldata.bin

bin · 348 B · SHA-256 ed121e756d63…d62b · Hugging Face

distil-whisper_distil-large-v3_594MB/AudioEncoder.mlmodelc/weights/weight.bin

bin · 338 MB · SHA-256 8f3ac62177a8…bc4d · Hugging Face

distil-whisper_distil-large-v3_594MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 091a36113489…508f · Hugging Face

distil-whisper_distil-large-v3_594MB/MelSpectrogram.mlmodelc/coremldata.bin

bin · 329 B · SHA-256 f3c5778c86d6…9a68 · Hugging Face

distil-whisper_distil-large-v3_594MB/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 365 KB · SHA-256 1f0c972cf2fd…4496 · Hugging Face

distil-whisper_distil-large-v3_594MB/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 a7a330a17952…fac2 · Hugging Face

distil-whisper_distil-large-v3_594MB/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 a7372960953a…97a8 · Hugging Face

distil-whisper_distil-large-v3_594MB/TextDecoder.mlmodelc/weights/weight.bin

bin · 228 MB · SHA-256 0a38bc3b78a2…8d6c · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 94b7b86bea50…8a33 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/AudioEncoder.mlmodelc/coremldata.bin

bin · 348 B · SHA-256 ed121e756d63…d62b · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/AudioEncoder.mlmodelc/weights/weight.bin

bin · 338 MB · SHA-256 98410d88d524…2a15 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 091a36113489…508f · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/MelSpectrogram.mlmodelc/coremldata.bin

bin · 329 B · SHA-256 f3c5778c86d6…9a68 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 365 KB · SHA-256 7a80bf139bea…4ef0 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 013f68d396d5…663d · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 db10bd19b00b…7b11 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoder.mlmodelc/weights/weight.bin

bin · 228 MB · SHA-256 4e8e3906c4f1…bc84 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoderContextPrefill.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 177b3e51ce24…372e · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoderContextPrefill.mlmodelc/coremldata.bin

bin · 380 B · SHA-256 e1fb28c51275…f781 · Hugging Face

distil-whisper_distil-large-v3_turbo_600MB/TextDecoderContextPrefill.mlmodelc/weights/weight.bin

bin · 5,86 MB · SHA-256 26266f85b383…7ae0 · Hugging Face

distil-whisper_distil-large-v3_turbo/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 b68eb75cef8a…bf4c · Hugging Face

distil-whisper_distil-large-v3_turbo/AudioEncoder.mlmodelc/coremldata.bin

bin · 348 B · SHA-256 273d6cd004f9…4f62 · Hugging Face

distil-whisper_distil-large-v3_turbo/AudioEncoder.mlmodelc/weights/weight.bin

bin · 1,19 GB · SHA-256 3a99a8d81ecb…5b68 · Hugging Face

distil-whisper_distil-large-v3_turbo/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 091a36113489…508f · Hugging Face

distil-whisper_distil-large-v3_turbo/MelSpectrogram.mlmodelc/coremldata.bin

bin · 329 B · SHA-256 f3c5778c86d6…9a68 · Hugging Face

distil-whisper_distil-large-v3_turbo/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 365 KB · SHA-256 7a80bf139bea…4ef0 · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 013f68d396d5…663d · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 db10bd19b00b…7b11 · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoder.mlmodelc/weights/weight.bin

bin · 228 MB · SHA-256 4e8e3906c4f1…bc84 · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoderContextPrefill.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 177b3e51ce24…372e · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoderContextPrefill.mlmodelc/coremldata.bin

bin · 380 B · SHA-256 e1fb28c51275…f781 · Hugging Face

distil-whisper_distil-large-v3_turbo/TextDecoderContextPrefill.mlmodelc/weights/weight.bin

bin · 5,86 MB · SHA-256 26266f85b383…7ae0 · Hugging Face

distil-whisper_distil-large-v3/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 195e35e9fbaa…625a · Hugging Face

distil-whisper_distil-large-v3/AudioEncoder.mlmodelc/coremldata.bin

bin · 348 B · SHA-256 273d6cd004f9…4f62 · Hugging Face

distil-whisper_distil-large-v3/AudioEncoder.mlmodelc/weights/weight.bin

bin · 1,19 GB · SHA-256 8406a888fff7…41db · Hugging Face

distil-whisper_distil-large-v3/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 091a36113489…508f · Hugging Face

distil-whisper_distil-large-v3/MelSpectrogram.mlmodelc/coremldata.bin

bin · 329 B · SHA-256 f3c5778c86d6…9a68 · Hugging Face

distil-whisper_distil-large-v3/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 365 KB · SHA-256 1f0c972cf2fd…4496 · Hugging Face

distil-whisper_distil-large-v3/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 a7a330a17952…fac2 · Hugging Face

distil-whisper_distil-large-v3/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 a7372960953a…97a8 · Hugging Face

distil-whisper_distil-large-v3/TextDecoder.mlmodelc/weights/weight.bin

bin · 228 MB · SHA-256 0a38bc3b78a2…8d6c · Hugging Face

openai_whisper-base.en/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 c4e096b2abd5…827e · Hugging Face

openai_whisper-base.en/AudioEncoder.mlmodelc/coremldata.bin

bin · 347 B · SHA-256 e316980638e2…96ba · Hugging Face

openai_whisper-base.en/AudioEncoder.mlmodelc/weights/weight.bin

bin · 39,3 MB · SHA-256 74f15e6d2f76…c1c7 · Hugging Face

openai_whisper-base.en/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 7f77e6457285…5d07 · Hugging Face

openai_whisper-base.en/MelSpectrogram.mlmodelc/coremldata.bin

bin · 328 B · SHA-256 dabdc5aa69f6…1662 · Hugging Face

openai_whisper-base.en/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 346 KB · SHA-256 ee77f9b67765…d6c1 · Hugging Face

openai_whisper-base.en/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 e870aac5de88…db8d · Hugging Face

openai_whisper-base.en/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 4b23ff9d9fe3…db43 · Hugging Face

openai_whisper-base.en/TextDecoder.mlmodelc/weights/weight.bin

bin · 99,3 MB · SHA-256 4649599bd2d9…6221 · Hugging Face

openai_whisper-base/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 c4e096b2abd5…827e · Hugging Face

openai_whisper-base/AudioEncoder.mlmodelc/coremldata.bin

bin · 347 B · SHA-256 e316980638e2…96ba · Hugging Face

openai_whisper-base/AudioEncoder.mlmodelc/weights/weight.bin

bin · 39,3 MB · SHA-256 061ff4d74e5d…642b · Hugging Face

openai_whisper-base/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 7f77e6457285…5d07 · Hugging Face

openai_whisper-base/MelSpectrogram.mlmodelc/coremldata.bin

bin · 328 B · SHA-256 dabdc5aa69f6…1662 · Hugging Face

openai_whisper-base/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 346 KB · SHA-256 35d74417ef9c…2efc · Hugging Face

openai_whisper-base/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 6ac1227740ec…6b95 · Hugging Face

openai_whisper-base/TextDecoder.mlmodelc/coremldata.bin

bin · 633 B · SHA-256 9f1f6fe40948…be7c · Hugging Face

openai_whisper-base/TextDecoder.mlmodelc/weights/weight.bin

bin · 99,3 MB · SHA-256 72325d42a4a4…d174 · Hugging Face

openai_whisper-large-v2_949MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 18a25d3e0440…99fd · Hugging Face

openai_whisper-large-v2_949MB/AudioEncoder.mlmodelc/coremldata.bin

bin · 347 B · SHA-256 7db300c721e9…6310 · Hugging Face

openai_whisper-large-v2_949MB/AudioEncoder.mlmodelc/weights/weight.bin

bin · 337 MB · SHA-256 9cde1ffb6ef9…7d8b · Hugging Face

openai_whisper-large-v2_949MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 562a52640a05…e9df · Hugging Face

Extraits de sources

3 extraits

Readme4 oct.huggingface.co/argmaxinc/whisperkit-coreml

--- pretty_name: WhisperKit viewer: false library_name: whisperkit tags: - whisper - whisperkit - coreml - asr - quantized - automatic-speech-recognition license: mit --- # WhisperKit ## Repo WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift ## Paper Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 ## Pro For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Readme11 juil.huggingface.co/argmaxinc/whisperkit-coreml

--- pretty_name: "WhisperKit" viewer: false library_name: whisperkit tags: - whisper - whisperkit - coreml - asr - quantized - automatic-speech-recognition --- # WhisperKit ## Repo WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift ## Paper Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 ## Pro For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Note4 oct.huggingface.co/argmaxinc/whisperkit-coreml

Source context: 10697053 downloads · 235 likes · Pipeline automatic-speech-recognition · Library whisperkit · Repo argmaxinc/whisperkit-coreml