How to use GlowLED/whisper-tiny-minds14-en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="GlowLED/whisper-tiny-minds14-en")
# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("GlowLED/whisper-tiny-minds14-en") model = AutoModelForSpeechSeq2Seq.from_pretrained("GlowLED/whisper-tiny-minds14-en", device_map="auto")
Fine-tuned openai/whisper-tiny on PolyAI/minds14 en-US (first 450 examples as train). Normalised WER 0.2341 (< 0.37). Use with WhisperForConditionalGeneration + WhisperProcessor.
openai/whisper-tiny
PolyAI/minds14
WhisperForConditionalGeneration
WhisperProcessor
# automatic-speech-recognition
Files info
