Update class name in the quick start

README.md

@@ -32,7 +32,7 @@ For more details on the model, please go to the upstream [model card](https://hu
 
 Pure-**Keras 3** conversion of [`openai/whisper-tiny`](https://huggingface.co/openai/whisper-tiny) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
-This is an **ASR** checkpoint (`WhisperSpeechToText`, 39M).
+This is an **ASR** checkpoint (`WhisperConditionalGenerate`, 39M).
 
 ## ✨ Quick start
 
@@ -43,10 +43,10 @@ os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 import soundfile as sf
 from kerasformers.models.whisper import (
     WhisperProcessor,
-    WhisperSpeechToText,
+    WhisperConditionalGenerate,
 )
 
-model = WhisperSpeechToText.from_weights("kerasformers/whisper_tiny")
+model = WhisperConditionalGenerate.from_weights("kerasformers/whisper_tiny")
 processor = WhisperProcessor.from_weights("kerasformers/whisper_tiny")
 
 audio, sr = sf.read("your_audio.wav", dtype="float32")  # 16 kHz mono
@@ -74,7 +74,7 @@ Load any Whisper variant the same way with `from_weights("kerasformers/<variant>
 - Prefer `WhisperProcessor.from_weights(...)` so mel bins match the variant (v3 uses 128).
 - Clips are padded to a 30 s window; chunk longer audio yourself.
 - See [Whisper docs](https://imvision12.github.io/KerasFormers/whisper/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
-- Community / upstream safetensors still work via the `hf:` prefix, e.g. `WhisperSpeechToText.from_weights("hf:openai/whisper-tiny")`.
+- Community / upstream safetensors still work via the `hf:` prefix, e.g. `WhisperConditionalGenerate.from_weights("hf:openai/whisper-tiny")`.
 
 ## Special Thanks