Models / whisper-large-v3

Whisper large-v3

OpenAI's largest multilingual speech recognition model: a convolutional stem over a 128-bin log-mel spectrogram, 32 encoder layers, and a 32-layer decoder that cross-attends to them, at width 1280.

1.5B parameterswhisperApache-2.0automatic-speech-recognitionaudioencoder-decodercross-attentionmultilingual

One clip (hf-internal-testing/librispeech_asr_dummy, clean/validation[0]), transcribed greedily through Linnet and through the reference stack.

Linnet

"Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.

transformers (reference)

Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.

The two transcripts differ.