openai/whisper · Discussions

#64 opened over 2 years ago by

Santi69

fine-tune whisper with CPU

#63 opened over 2 years ago by

Santi69

Connection Error out

#62 opened over 2 years ago by deleted

Error while running in docker

5

#61 opened over 2 years ago by

wustir

Add file button try

#60 opened over 2 years ago by

Burhanerdem

WHAT THE HECK?!?

#59 opened over 2 years ago by

A bunch of E's

#58 opened over 2 years ago by

I WAS A CAT!

#57 opened over 2 years ago by

WOW

#56 opened over 2 years ago by

jaduido

Why does it just say brrrrr

#55 opened over 2 years ago by

nununana

"Well, let's see how this does..."

#54 opened over 2 years ago by

merhabachai

"well, let's see how this does...

#53 opened over 2 years ago by

merhabachai

understandable

#52 opened over 2 years ago by

Axole

Open AI Whisper - Speech recognition model

#51 opened over 2 years ago by

natraj

Tried it with an English speaking choir, not very successful.

#49 opened over 2 years ago by

Windowsfreak

Not quite right

#48 opened over 2 years ago by

Windowsfreak

Try to do code-switching. It seems perfect.

6

7

#45 opened over 2 years ago by

ryL

🚩 Report : Not working

#44 opened over 2 years ago by

dsrhdhg

Start the engine!

#42 opened over 2 years ago by

WHY!?!?!?

#39 opened over 2 years ago by

C

#38 opened over 2 years ago by

B

#37 opened over 2 years ago by

I tried this with my alphabet toy!

#36 opened over 2 years ago by

Thank you.

#35 opened over 2 years ago by

jmalfara

Hamburger!

#34 opened over 2 years ago by

First time using Whisper (purposefully talking "normally" i.e. not perfectly enunciating). Amazing!

#33 opened over 2 years ago by

ncfausti

aaaatest

#32 opened over 2 years ago by

dongxxx

Detecting sound triggers before noise removal

#31 opened over 2 years ago by

little-bang

About filler words detection (a.k.a. full breaks / disfluency words e.g. eh, umm, ahh)

9

#30 opened over 2 years ago by

rmajasol

Time stamp on word level & Speaker identification

11

#29 opened over 2 years ago by

chan-K

I create a "half" streaming audio transcriber demo

#28 opened over 2 years ago by

zhenxuan

Fork handles

#27 opened over 2 years ago by

pogpog

🇻🇳

#26 opened over 2 years ago by

thanhnguyen

Tried saying "ẹkáàrọ" (Nigeria yoruba)

#25 opened over 2 years ago by

AmbroseIkpele

testing Sunday

#24 opened over 2 years ago by

rogermt

🇺🇸🇧🇷🇺🇸

#23 opened over 2 years ago by

radames

🇯🇵 💯

#22 opened over 2 years ago by

nbroad

Testing out French informal discourse

#21 opened over 2 years ago by

julien-c

"Can you feel the sunshine. Does it brighten up your day?"

#20 opened over 2 years ago by

testing

#19 opened over 2 years ago by

mishig

"I missed the part where that's my problem"

#18 opened over 2 years ago by

Speaking gibberish on purpose gives funny results

#17 opened over 2 years ago by

It understands me singing the Pokemon Battle Dimension lyrics

#16 opened over 2 years ago by

Go home Whisper, you're drunk!

#15 opened over 2 years ago by

lewtun

French test

#14 opened over 2 years ago by

victor

Practicing my Russian 🇷🇺 (it has been a while)

3

#13 opened over 2 years ago by

mishig

I need to improve my 🇫🇷 accent. Whisper is mostly getting it

5

#12 opened over 2 years ago by

mishig

Reporting bug/inappropriate handling of Cantonese language

#11 opened over 2 years ago by

cuichungman

Streaming audio

#10 opened over 2 years ago by

dimitrios

bug