openai/whisper · Discussions

#80 opened over 2 years ago by

SameerMahajan

added column not getting saved in dataset

#78 opened over 2 years ago by

SameerMahajan

Even when the speakers starts talking after 10 sec, Whisper make the first timestamp to start at sec 0. How could I change that?

#77 opened over 2 years ago by

romain130492

Can Whisper be used for real-time speech to text?

👍 1

11

#76 opened over 2 years ago by

ImagineThis

Fine-tune Whisper on a Local Custom dataset

#75 opened almost 3 years ago by

hamza94

Distinguishing between speech and non speech

3

#74 opened almost 3 years ago by

CarelessWhisperer

useWhisper a React Hook for OpenAI Whisper API

🤯 1

#73 opened almost 3 years ago by

chengsokdara

Time-codes from whisper

5

#71 opened almost 3 years ago by

EranML

wagahai

#68 opened almost 3 years ago by

wasao238

issues working with marathi numbers

35

#66 opened almost 3 years ago by

SameerMahajan

My Dutch-Whisper experiment.

❤️ 3

#65 opened almost 3 years ago by

Arjanneke

adding new tokens to the new fine-tune model

❤️ 1

#64 opened almost 3 years ago by

Santi69

fine-tune whisper with CPU

#63 opened almost 3 years ago by

Santi69

Connection Error out

#62 opened almost 3 years ago by deleted

Error while running in docker

5

#61 opened almost 3 years ago by

wustir

Add file button try

#60 opened almost 3 years ago by

Burhanerdem

WHAT THE HECK?!?

#59 opened almost 3 years ago by

A bunch of E's

#58 opened almost 3 years ago by

I WAS A CAT!

#57 opened almost 3 years ago by

WOW

#56 opened almost 3 years ago by

jaduido

Why does it just say brrrrr

#55 opened about 3 years ago by

nununana

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

#54 opened about 3 years ago by

merhabachai

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

#53 opened about 3 years ago by

merhabachai

understandable

#52 opened about 3 years ago by

Axole

Open AI Whisper - Speech recognition model

#51 opened about 3 years ago by

natraj

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

#49 opened about 3 years ago by

Windowsfreak

Not quite right

#48 opened about 3 years ago by

Windowsfreak

Try to do code-switching. It seems perfect.

🤯 🤗 6

7

#45 opened about 3 years ago by

ryL

🚩 Report : Not working

#44 opened about 3 years ago by

dsrhdhg

Start the engine!

#42 opened about 3 years ago by

WHY!?!?!?

#39 opened about 3 years ago by

C

#38 opened about 3 years ago by

B

#37 opened about 3 years ago by

I tried this with my alphabet toy!

#36 opened about 3 years ago by

Thank you.

#35 opened about 3 years ago by

jmalfara

Hamburger!

#34 opened about 3 years ago by

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

#33 opened about 3 years ago by

ncfausti

aaaatest

#32 opened about 3 years ago by

dongxxx

Detecting sound triggers before noise removal

#31 opened about 3 years ago by

little-bang

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

9

#30 opened about 3 years ago by

rmajasol

Time stamp on word level & Speaker identification

11

#29 opened about 3 years ago by

chan-K

I create a "half" streaming audio transcriber demo

#28 opened about 3 years ago by

zhenxuan

Fork handles

#27 opened about 3 years ago by

pogpog

🇻🇳

#26 opened about 3 years ago by

thanhnguyen

Tried saying "ẹkáàrọ" (Nigeria yoruba)