Card: needle.transcribe is the entry point

README.md

@@ -62,12 +62,11 @@ The Python package and the source are on [GitHub](https://github.com/cactus-comp
 ```python
 import needle
 
-whistle = needle.Whistle()
-print(whistle.transcribe("clip.wav")["text"])
+print(needle.transcribe("clip.wav")["text"])
 # turn off the kitchen lights
 ```
 
-Every call returns the text, the language, the milliseconds to the first token and the decoder's tokens per second after it. `word_timestamps=True` adds each word with its start, end and probability, `keywords=[...]` favours the names your users say, and `language="de"` forces the language instead of detecting it. The engine and the weights are fetched once and cached. `needle whistle playground` transcribes from the microphone, and `needle whistle compare` puts Whistle next to Whisper and Moonshine on the same clip.
+Every call returns the text, the language, the milliseconds to the first token and the decoder's tokens per second after it. `word_timestamps=True` adds each word with its start, end and probability, `keywords=[...]` favours the names your users say, and `language="de"` forces the language instead of detecting it. The engine and the weights are fetched once and cached. `needle.Whistle()` is the same model as an object, for `embed(audio)` or to hold one tuned `.cact`. `needle whistle playground` transcribes from the microphone, and `needle whistle compare` puts Whistle next to Whisper and Moonshine on the same clip.
 
 ## With Needle