Automatic Speech Recognition
Transformers
Safetensors
seamless_m4t_v2
audio
speech
african-languages
multilingual
simba
low-resource
speech-recognition
asr
Instructions to use UBC-NLP/Simba-S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UBC-NLP/Simba-S with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UBC-NLP/Simba-S")# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("UBC-NLP/Simba-S") model = AutoModelForSpeechSeq2Seq.from_pretrained("UBC-NLP/Simba-S", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 6b69da23df738e9760e0a97502ff053293b9affcb172e71abb9c3532ab1814a0
- Size of remote file:
- 5.17 MB
- SHA256:
- 026a76827537db9f1348e4d5aaa127bb10a2f2ff633243f3a52d16be82d73f9d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.