Automatic Speech Recognition
audio
ericchin's picture
Update README.md
e112c07 verified
|
raw
history blame
39.4 kB
metadata
license: apache-2.0
language:
  - en
  - zh
  - de
  - es
  - ru
  - ko
  - fr
  - ja
  - pt
  - tr
  - pl
  - ca
  - nl
  - ar
  - sv
  - it
  - id
  - hi
  - fi
  - vi
  - he
  - uk
  - el
  - ms
  - cs
  - ro
  - da
  - hu
  - ta
  - 'no'
  - th
  - ur
  - hr
  - bg
  - lt
  - la
  - mi
  - ml
  - cy
  - sk
  - te
  - fa
  - lv
  - bn
  - sr
  - az
  - sl
  - kn
  - et
  - mk
  - br
  - eu
  - is
  - hy
  - ne
  - mn
  - bs
  - kk
  - sq
  - sw
  - gl
  - mr
  - pa
  - si
  - km
  - sn
  - yo
  - so
  - af
  - oc
  - ka
  - be
  - tg
  - sd
  - gu
  - am
  - yi
  - lo
  - uz
  - fo
  - ht
  - ps
  - tk
  - nn
  - mt
  - sa
  - lb
  - my
  - bo
  - tl
  - mg
  - as
  - tt
  - haw
  - ln
  - ha
  - ba
  - jw
  - su
tags:
  - audio
  - automatic-speech-recognition
base_model: openai/whisper-small
pipeline_tag: automatic-speech-recognition

Whisper-small 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