Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use wu-kiot/whisper-small-fc-am with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wu-kiot/whisper-small-fc-am with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="wu-kiot/whisper-small-fc-am")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("wu-kiot/whisper-small-fc-am") model = AutoModelForSpeechSeq2Seq.from_pretrained("wu-kiot/whisper-small-fc-am", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 5c24cc86e8712a3ed73b6a60211b5d3a4cb320ef9c23681bec485cdcd49dbe5f
- Size of remote file:
- 967 MB
- SHA256:
- cf6d48964cbfd5caee78b6bfd3d2ac6249e82c9fcbf45cc42f183f2cd8fed795
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.