Instructions to use nguyenvulebinh/wav2vec2-bartpho with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nguyenvulebinh/wav2vec2-bartpho with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nguyenvulebinh/wav2vec2-bartpho")# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("nguyenvulebinh/wav2vec2-bartpho") model = AutoModelForSpeechSeq2Seq.from_pretrained("nguyenvulebinh/wav2vec2-bartpho") - Notebooks
- Google Colab
- Kaggle
Can we use force alignment with this model ?
#1
by leminhnguyen - opened
Dear author, thank you for your amazing model. It's quite impressive for me with the performance. I have some questions about this model:
- How does the model predict the timestamp ? What about the training labels for this model ?
- Can we force alignments and get the confident scores with this model ?
Hope to hear from you soon !