Models / whisper-tiny

Whisper tiny

OpenAI's smallest multilingual speech recognition model: a convolutional stem over a log-mel spectrogram, four encoder layers, and a four-layer decoder that cross-attends to them.

37.8M 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 are identical.