Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Vietnamese
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use joey234/whisper-medium-vi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joey234/whisper-medium-vi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="joey234/whisper-medium-vi")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("joey234/whisper-medium-vi") model = AutoModelForSpeechSeq2Seq.from_pretrained("joey234/whisper-medium-vi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from joey234/whisper-medium-vi: direct link, hf CLI and curl.
- Browser
- Download file 198 Bytes
-
https://huggingface.co/joey234/whisper-medium-vi/resolve/main/eval_results.json
- Command line
-
hf download hf://joey234/whisper-medium-vi/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/joey234/whisper-medium-vi/resolve/main/eval_results.json
198 Bytes
| { | |
| "epoch": 624.0, | |
| "eval_loss": 0.7136163115501404, | |
| "eval_runtime": 242.798, | |
| "eval_samples_per_second": 5.095, | |
| "eval_steps_per_second": 0.161, | |
| "eval_wer": 15.492494795661225 | |
| } |