avemio
/

German-RAG-WHISPER-LARGE-v3-TURBO-HESSIAN-AI

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

avemio-digital commited on Jan 7

Commit

9c97ccc

·

verified ·

1 Parent(s): e497c89

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -38,14 +38,14 @@ This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://hu
 ## Evaluations - Word error rate
-| Dataset                             | openai-whisper-large-v3-turbo | GRAG-WHISPER-LARGE-v3-TURBO | primeline-whisper-large-v3-turbo-german |
 |-------------------------------------|-------------------------------|-------------------------|-----------------------------------|
-| Tuda-De                             | 8.195                         | 6.360                   | 6.441                             |
-| common_voice_19_0                   | 3.839                         | 3.249                   | 3.217                             |
-| multilingual librispeech            | 3.202                         | 2.071                   | 2.067                             |
-| All                                 | 3.641                         | 2.633                   | 2.630                             |
-The data and code for evaluations are available [here](https://huggingface.co/datasets/flozi00/asr-german-mixed-evals)
 ### Training data
 The training data for this model includes conversations of spoken German with a mix of english business phrases included. The data was carefully selected and processed to optimize recognition performance. The dataset will not be published because of unclear situation if the data would be used for voice-cloning. The rights to use the collected data are only for the intended use to train speech-to-text models.

 ## Evaluations - Word error rate
+| Test-Dataset                             | openai-whisper-large-v3-turbo | **GRAG-WHISPER-LARGE-v3-TURBO** | primeline-whisper-large-v3-turbo-german |
 |-------------------------------------|-------------------------------|-------------------------|-----------------------------------|
+| Tuda-De                             | 8.195                         | **6.360**                   | 6.441                             |
+| common_voice_19_0                   | 3.839                         | 3.249                   | **3.217**                             |
+| multilingual librispeech            | 3.202                         | 2.071                   | **2.067**                             |
+| All                                 | 3.641                         | 2.633                   | **2.630**                             |
+The data and code for evaluations are available [here](https://huggingface.co/datasets/avemio/ASR-GERMAN-MIXED-EVALS-GRAG)
 ### Training data
 The training data for this model includes conversations of spoken German with a mix of english business phrases included. The data was carefully selected and processed to optimize recognition performance. The dataset will not be published because of unclear situation if the data would be used for voice-cloning. The rights to use the collected data are only for the intended use to train speech-to-text models.