Instructions to use microsoft/speecht5_asr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/speecht5_asr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/speecht5_asr")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("microsoft/speecht5_asr") model = AutoModelForSpeechSeq2Seq.from_pretrained("microsoft/speecht5_asr") - Notebooks
- Google Colab
- Kaggle
Fix config files
#3
by Matthijs - opened
No description provided.
Matthijs changed pull request title from fix-config to Fix config files
I made changes to the code to support fine-tuning, which required changes to the config files. Notably the tokenizer needs to have the mask and ctc_blank tokens, even if not used during inference.
Matthijs changed pull request status to open
nielsr changed pull request status to merged