How to use mkrausio/whisper-captioning-large-v3-turbo-v0.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mkrausio/whisper-captioning-large-v3-turbo-v0.2")
# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mkrausio/whisper-captioning-large-v3-turbo-v0.2") model = AutoModelForSpeechSeq2Seq.from_pretrained("mkrausio/whisper-captioning-large-v3-turbo-v0.2", device_map="auto")
Trained on 2.6M samples for 7 epochs with linear decreasing learnrate and a warmup of 2000 steps.
Files info
Base model
