Whisper-Base

Automatic Speech Recognition (ASR) transcribes spoken audio to text with multilingual support and speech translation to English

Model Properties

Audio is sampled at 16 kHz and converted to a 10s window. A transformer encoder processes the spectrogram, and a transformer decoder autoregressively predicts text tokens

License name: Apache License 2.0
Number of parameters: 74M
Model Size: 155 MB
Select device..

Technical Details

Audio Sample Rate Hz: 16,000
Tokenizer: Whisper tokenizer (multilingual)
Numerical Scheme: Mixed precision
Inference API: C++, Python
Compiled Model:

Performance Metrics

Load Time In Sec 1.35
TPS 25.16

Explore Related Models

hailo whisper-base automatic speech recognition gen ai model
GenAI Models
Whisper-Small
Generate text responses to prompts, enabling natural language understanding, multilingual support, content creation and advanced reasoning
hailo whisper-base automatic speech recognition gen ai model
GenAI Models
Whisper-Tiny
Generate text responses to prompts, enabling natural language understanding, multilingual support, content creation and advanced reasoning