How to use Gradient-Research/Gradient-Transcribe1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Gradient-Research/Gradient-Transcribe1", trust_remote_code=True)
# Load model directly from transformers import AutoModelForConditionalGeneration model = AutoModelForConditionalGeneration.from_pretrained("Gradient-Research/Gradient-Transcribe1", trust_remote_code=True, dtype="auto")
This model is alot faster than other ASR models and I like it. Just it bugs on some tasks.
· Sign up or log in to comment
