Ichigo: Local real-time voice AI
31–40 of 45 posts
Re: Ichigo: Local real-time voice AI
#32Re: Ichigo: Local real-time voice AI
#33Finally I can use one of the random facts that have entered my brain for decades now even though I can't remember where my keys are. If I remember correctly, "ichigo" means strawberry in japanese. You are welcome.
Sorry, you're wrong. It means 1 5. Just kidding, it is strawberry but it can also be read as one and five. However, it is not fifteen.
Can you help me wrap my brain around this? Does it mean six? I'm struggling to understand how a word can mean two numbers and how this would actually be used in a conversation.
Thanks. I'm curious and trying to search for this to understand just returns anime.
Re: Ichigo: Local real-time voice AI
#34Earlier quoted context omitted.
Sorry, you're wrong. It means 1 5. Just kidding, it is strawberry but it can also be read as one and five. However, it is not fifteen.
> it can also be read as one and five. However, it is not fifteen. Can you help me wrap my brain around this? Does it mean six? I'm struggling to understand how a word can mean two numbers and how this would actually be used in a conversation. Thanks. I'm curious and trying to search for this to understand just returns anime.
Ichi is the word for 1. Go is the word for 5.
Re: Ichigo: Local real-time voice AI
#35Earlier quoted context omitted.
Is this a continuation of the meme that GPT can't identify the number of "R"s in "strawberry"?
> How many 'r's are in the word 'ichigo'? GPT 4o: The word "ichigo," which is the Romanized spelling (romaji) of いちご, contains one "r." It appears in the letter "r" in "chi," as the "ch" sound in romaji represents a combination of the "r" sound from "r" and "t" sound from "i." Thank you chatgpt. I'm glad we've burned down a bunch of forests for this. You can consistently get the right answer with a prompt of: > Write…
There are no “r”s in the word “ichigo.”
Maybe your instructions are bad.
Re: Ichigo: Local real-time voice AI
#36Earlier quoted context omitted.
> it can also be read as one and five. However, it is not fifteen. Can you help me wrap my brain around this? Does it mean six? I'm struggling to understand how a word can mean two numbers and how this would actually be used in a conversation. Thanks. I'm curious and trying to search for this to understand just returns anime.
> I'm struggling to understand how a word can mean two numbers Ichi is the word for 1. Go is the word for 5.
Can't believe I fell for that.
Re: Ichigo: Local real-time voice AI
#37Finally I can use one of the random facts that have entered my brain for decades now even though I can't remember where my keys are. If I remember correctly, "ichigo" means strawberry in japanese. You are welcome.
Re: Ichigo: Local real-time voice AI
#38Earlier quoted context omitted.
Sorry, you're wrong. It means 1 5. Just kidding, it is strawberry but it can also be read as one and five. However, it is not fifteen.
> it can also be read as one and five. However, it is not fifteen. Can you help me wrap my brain around this? Does it mean six? I'm struggling to understand how a word can mean two numbers and how this would actually be used in a conversation. Thanks. I'm curious and trying to search for this to understand just returns anime.
Re: Ichigo: Local real-time voice AI
#39Finally I can use one of the random facts that have entered my brain for decades now even though I can't remember where my keys are. If I remember correctly, "ichigo" means strawberry in japanese. You are welcome.
Re: Ichigo: Local real-time voice AI
#40Earlier quoted context omitted.
Actually, it does. You can turn on the transcription feature from the bottom right corner and even type to Ichigo if you want. We didn’t show it in the launch video since we were focusing on the verbal interaction side of things.
Ah, I see now. To clarify, while you can enable transcription to see what Ichigo says, Ichigo's design skips directly from audio to speech representations without creating a text transcription of the user’s input. This makes interactions faster but does mean that the user's spoken input isn't transcribed to text. The flow we use is Speech → Encoder → Speech Representations → LLM → Text → TTS. By skipping the text ste…