As a translator who billed approximately 750,000 words last year, yes. Speech to text software is another good tool for circumventing this bottleneck that many translators use.
Japanese to English translator here. The general rule of thumb (that is often used for billing estimates) is that N Japanese characters = N/2 English words.
So if you have a Japanese source text that is 2,000 characters, the English translation will be around 1,000 words.
I tested a translation (one sentence) from a previous job:
Japanese: 94 characters, 128 tokens
English: 39 words (232 characters), 47 tokens
Seems quite unbalanced given that the amount of "information" in the two is equivalent.
Is the script you use publicly available somewhere?