Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use razhan/whisper-base-zza with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use razhan/whisper-base-zza with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="razhan/whisper-base-zza")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("razhan/whisper-base-zza") model = AutoModelForSpeechSeq2Seq.from_pretrained("razhan/whisper-base-zza", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from razhan/whisper-base-zza: direct link, hf CLI and curl.
- Browser
- Download file 255 Bytes
-
https://huggingface.co/razhan/whisper-base-zza/resolve/main/eval_results.json
- Command line
-
hf download hf://razhan/whisper-base-zza/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/razhan/whisper-base-zza/resolve/main/eval_results.json
255 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_cer": 1.0132317562149158, | |
| "eval_loss": 4.095639228820801, | |
| "eval_runtime": 18.0801, | |
| "eval_samples": 50, | |
| "eval_samples_per_second": 2.765, | |
| "eval_steps_per_second": 0.055, | |
| "eval_wer": 1.2574447646493756 | |
| } |