Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
German
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use HanCreation/whisper-tiny-german-HanNeurAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HanCreation/whisper-tiny-german-HanNeurAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="HanCreation/whisper-tiny-german-HanNeurAI")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("HanCreation/whisper-tiny-german-HanNeurAI") model = AutoModelForSpeechSeq2Seq.from_pretrained("HanCreation/whisper-tiny-german-HanNeurAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Dean Hans Felandio Setiadi Saputra commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,7 @@ It achieves the following results on the evaluation set:
|
|
| 38 |
- Wer: 31.4346
|
| 39 |
|
| 40 |
This model is part of my school project, it uses shuffled 100k rows of train dataset since the computation power is limited.
|
|
|
|
| 41 |
Additional information can be found in this github: [HanCreation/Whisper-Tiny-German](https://github.com/HanCreation/Whisper-Tiny-German)
|
| 42 |
|
| 43 |
### Training hyperparameters
|
|
|
|
| 38 |
- Wer: 31.4346
|
| 39 |
|
| 40 |
This model is part of my school project, it uses shuffled 100k rows of train dataset since the computation power is limited.
|
| 41 |
+
|
| 42 |
Additional information can be found in this github: [HanCreation/Whisper-Tiny-German](https://github.com/HanCreation/Whisper-Tiny-German)
|
| 43 |
|
| 44 |
### Training hyperparameters
|