I don't use Apple products, but I've used Whisper along with Python in the past. It's a great API. Also, I see that you've killed and beheaded the Abominable Snowman. Congrats. The villagers are safe now. 😊
HAHAHAHA! I was fortunate to meet a trader of hand-made Romanian masks in the Carpathian mountains and purchased it a few months back. It's now one of my favorite things from my travels. I'm thinking about making a non-Apple version of this video in the near future.
Interesting! I have been working with whisperX and whisper-timestamped on my MacBook so far and wasn't aware of MLX. Thanks for sharing! But since you emphasize the word level timestamps: with standard whisper those are known to be very inaccurate (i.e. pretty much unusable - whisper is simply not trained to predict timestamps). So, are you suggesting that timestamps in whisper-mlx are better?
Not yet, but I suspect that wil be a added soon. MLX is covering a wide ground right now, but over the next few months I expect that they will go deeper with that wide net both through their own work and community pull requests
I don't use Apple products, but I've used Whisper along with Python in the past. It's a great API. Also, I see that you've killed and beheaded the Abominable Snowman. Congrats. The villagers are safe now. 😊
HAHAHAHA! I was fortunate to meet a trader of hand-made Romanian masks in the Carpathian mountains and purchased it a few months back. It's now one of my favorite things from my travels. I'm thinking about making a non-Apple version of this video in the near future.
Thanks for sharing.
Thanks for watching!
thank you for your videos
you are really a great teacher
your channel is a gem
Interesting! I have been working with whisperX and whisper-timestamped on my MacBook so far and wasn't aware of MLX. Thanks for sharing! But since you emphasize the word level timestamps: with standard whisper those are known to be very inaccurate (i.e. pretty much unusable - whisper is simply not trained to predict timestamps). So, are you suggesting that timestamps in whisper-mlx are better?
Do you know which languages it speaks?
What about speaker diarization with mlx?
Not yet, but I suspect that wil be a added soon. MLX is covering a wide ground right now, but over the next few months I expect that they will go deeper with that wide net both through their own work and community pull requests