Instructions to use Atotti/qwen2-audio-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Atotti/qwen2-audio-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Atotti/qwen2-audio-encoder")# Load model directly from transformers import AutoModelForMultimodalLM model = AutoModelForMultimodalLM.from_pretrained("Atotti/qwen2-audio-encoder", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Can this model weight directly replace the original Whisper weight?
#1
by mifanbushipeicai - opened
Thank you for your continuous efforts in extracting the Encoder.
Does this repo provide exactly the same calling methods and features as the original Whisper large v3, such as interfaces, data precision, and batch processing (e.g., automatic padding to 30 seconds), etc.?