Whisper WebGPU
Real-time speech recognition
English
Turkish
Chinese
German
Spanish/Castilian
Russian
Korean
French
Japanese
Portuguese
Polish
Catalan/Valencian
Dutch/Flemish
Arabic
Swedish
Italian
Indonesian
Hindi
Finnish
Vietnamese
Hebrew
Ukrainian
Greek
Malay
Czech
Romanian/Moldavian/Moldovan
Danish
Hungarian
Tamil
Norwegian
Thai
Urdu
Croatian
Bulgarian
Lithuanian
Latin
Maori
Malayalam
Welsh
Slovak
Telugu
Persian
Latvian
Bengali
Serbian
Azerbaijani
Slovenian
Kannada
Estonian
Macedonian
Breton
Basque
Icelandic
Armenian
Nepali
Mongolian
Bosnian
Kazakh
Albanian
Swahili
Galician
Marathi
Punjabi/Panjabi
Sinhala/Sinhalese
Khmer
Shona
Yoruba
Somali
Afrikaans
Occitan
Georgian
Belarusian
Tajik
Sindhi
Gujarati
Amharic
Yiddish
Lao
Uzbek
Faroese
Haitian Creole/Haitian
Pashto/Pushto
Turkmen
Nynorsk
Maltese
Sanskrit
Luxembourgish/Letzeburgesch
Myanmar/Burmese
Tibetan
Tagalog
Malagasy
Assamese
Tatar
Hawaiian
Lingala
Hausa
Bashkir
Javanese
Sundanese
Whisper Small
Whisper Base
Whisper Tiny
Whisper Small En
Whisper Base En
Whisper Tiny En
Whisper Base Tr
Whisper Small Tr
Load Model
Start Recording
Speech Detection Parameters
Energy Threshold: 0.125
Energy Scale: 2.0
Min Silence (s): 0.60
Speech Hangover (s): 0.20
Min Speech (s): 0.30
Hysteresis: 1.20
Min Energy Integral: 25.000
Audio Stats
Current Energy: 0.0000
Average Energy: 0.0000
Peak Energy: 0.0000
Buffer Duration: 0.00s
Detected Speech Segments (0)