Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use jstoone/whisper-tiny-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jstoone/whisper-tiny-en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jstoone/whisper-tiny-en")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("jstoone/whisper-tiny-en") model = AutoModelForSpeechSeq2Seq.from_pretrained("jstoone/whisper-tiny-en") - Notebooks
- Google Colab
- Kaggle
👷♀️ Fix WER display value to be zero-based percentage.
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
-
value:
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.9035
|
| 36 |
-
- Wer Ortho:
|
| 37 |
-
- Wer:
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
+
value: 0.35723514211886304
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.9035
|
| 36 |
+
- Wer Ortho: 0.354643
|
| 37 |
+
- Wer: 0.357235
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|