whisper --model tiny --language en hpr3348.wav

Comments

Subscribe to the comments RSS feed.

Comment #1 posted on 2021-06-02T05:24:23Z by HawkinsTheWizard

hpr3348 feedback

I have been wanting to comment about this for some time.
The quality of the audio is somewhat important but not a qualifier.
But what I at least WANT is the level of volume to be normalised at 95%. Its hard to hear in a noisy environment like a car or places with background noise.
This is easy for a submitted sample. Run all input/submits through a normaliser/compressor.
Volume checks in mumble/radio should also normalise.

Comment #2 posted on 2021-06-02T14:22:04Z by Dave Morriss

I was trying to remember "This American Life"

Listening to this I have remembered what I was complaining about in the show. I was referring to podcasts (and presumably radio shows) like "This American Life" which "interview" people but "translate" what they are saying over the top of them.

This is a "style" that many broadcasters seem to have adopted. Many of the BBC podcasts I have stopped listening to do this too. I find it distracting and insulting to the interviewee. It seems to be an example of media people reinterpreting what experts are saying in many cases, and we know how much misinformation comes from this practice.

If this is "professional" I don't want to have anything to do with it!

<< First, < Previous, Next >, Latest >>

Leave Comment

Note to Verbose Commenters
If you can't fit everything you want to say in the comment below then you really should record a response show instead.

Note to Spammers
All comments are moderated. All links are checked by humans. We strip out all html. Feel free to record a show about yourself, or your industry, or any other topic we may find interesting. We also check shows for spam :).