kerasformers/whisper_large_v3

See our collection for all versions of Whisper.

Run Whisper with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/whisper_large_v3

Paper: Robust Speech Recognition via Large-Scale Weak Supervision (arXiv:2212.04356) · HF Papers

Whisper is a multilingual encoder-decoder ASR model trained on large-scale weak supervision. Use task="transcribe" to keep the source language or task="translate" to render English. Pass language=None to let the model detect the spoken language. Output is cased and punctuated.

For more details on the model, please go to the upstream model card.

Pure-Keras 3 conversion of openai/whisper-large-v3 for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an ASR checkpoint (WhisperSpeechToText, 128 mel bins).

✨ Quick start

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

import soundfile as sf
from kerasformers.models.whisper import (
    WhisperProcessor,
    WhisperSpeechToText,
)

model = WhisperSpeechToText.from_weights("kerasformers/whisper_large_v3")
processor = WhisperProcessor.from_weights("kerasformers/whisper_large_v3")

audio, sr = sf.read("your_audio.wav", dtype="float32")  # 16 kHz mono
# task="transcribe" keeps the source language; "translate" -> English.
text = model.generate(audio, processor, language="en", task="transcribe")
print(repr(text[0]))

Load any Whisper variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub	Notes
whisper_tiny	kerasformers/whisper_tiny	39M
whisper_base	kerasformers/whisper_base	74M
whisper_small	kerasformers/whisper_small	244M
whisper_medium	kerasformers/whisper_medium	769M
whisper_large	kerasformers/whisper_large	1.55B
whisper_large_v2	kerasformers/whisper_large_v2	1.55B
whisper_large_v3	kerasformers/whisper_large_v3	128 mel bins
whisper_large_v3_turbo	kerasformers/whisper_large_v3_turbo	4 decoder layers

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• 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 and Loading Weights.
• Community / upstream safetensors still work via the hf: prefix, e.g. WhisperSpeechToText.from_weights("hf:openai/whisper-large-v3").

Special Thanks

A huge thank you to the OpenAI Whisper authors for creating and releasing these models.

License: Apache 2.0.