Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2") model = AutoModelForSpeechSeq2Seq.from_pretrained("qmeeus/whisper-small-multilingual-spoken-ner-end2end-v2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 1.42, | |
| "eval_combined_wer": 0.1491414618777568, | |
| "eval_f1_score": 0.7163398692810456, | |
| "eval_label_f1": 0.8200435729847495, | |
| "eval_loss": 0.2754737436771393, | |
| "eval_runtime": 117.0137, | |
| "eval_samples": 1000, | |
| "eval_samples_per_second": 8.546, | |
| "eval_steps_per_second": 0.137, | |
| "eval_wer": 0.08582479210984335 | |
| } |