Update README.md
Browse files
README.md
CHANGED
|
@@ -45,6 +45,16 @@ This model can be used in various application areas, including
|
|
| 45 |
| tiny whisper | 37.8M | [link](https://huggingface.co/primeline/whisper-tiny-german) |
|
| 46 |
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Training data
|
| 49 |
The training data for this model includes a large amount of spoken German from various sources. The data was carefully selected and processed to optimize recognition performance.
|
| 50 |
|
|
|
|
| 45 |
| tiny whisper | 37.8M | [link](https://huggingface.co/primeline/whisper-tiny-german) |
|
| 46 |
|
| 47 |
|
| 48 |
+
## Evaluations
|
| 49 |
+
|
| 50 |
+
| Dataset | openai-whisper-large-v3-turbo | openai-whisper-large-v3 | primeline-whisper-large-v3-german | nyrahealth-CrisperWhisper | primeline-whisper-large-v3-turbo-german |
|
| 51 |
+
|---------------------------------|-------------------------------|-------------------------|----------------------------------|---------------------------|----------------------------------------|
|
| 52 |
+
| common_voice_19_0 | 6.31 | 5.84 | 4.30 | 4.14 | 4.28 |
|
| 53 |
+
| Tuda-De | 11.45 | 11.21 | 9.89 | 13.88 | 8.10 |
|
| 54 |
+
| multilingual librispeech | 18.03 | 17.69 | 13.46 | 10.10 | 4.71 |
|
| 55 |
+
| All | 14.16 | 13.79 | 10.51 | 8.48 | 4.75 |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
### Training data
|
| 59 |
The training data for this model includes a large amount of spoken German from various sources. The data was carefully selected and processed to optimize recognition performance.
|
| 60 |
|