Hugging Face's logo

saattrupdan
/
alvenir-wav2vec2-base-cv8-da

Automatic Speech Recognition
Transformers
PyTorch
Danish
wav2vec2
Eval Results
Inference Endpoints
Model card Files Community
saattrupdan commited on
Commit
98d042a
•
1 Parent(s): 2cdbc39

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  name: Danish Common Voice 8.0
20
  metrics:
21
  - type: wer
22
- value: 46.05
23
  - task:
24
  type: automatic-speech-recognition
25
  dataset:
@@ -27,7 +27,7 @@ model-index:
27
  name: Alvenir ASR test dataset
28
  metrics:
29
  - type: wer
30
- value: 41.08
31
  ---
32
 
33
  # Alvenir-Wav2vec2-base-CV8-da
@@ -43,5 +43,5 @@ The model achieves the following WER scores (lower is better):
43
 
44
  | **Dataset** | **WER without LM** | **WER with 5-gram LM** |
45
  | :---: | ---: | ---: |
46
- | [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) | 46.05 | xx.xx |
47
- | [Alvenir test set](https://huggingface.co/datasets/Alvenir/alvenir_asr_da_eval) | 41.08 | xx.xx |
 
19
  name: Danish Common Voice 8.0
20
  metrics:
21
  - type: wer
22
+ value: 39.86
23
  - task:
24
  type: automatic-speech-recognition
25
  dataset:
 
27
  name: Alvenir ASR test dataset
28
  metrics:
29
  - type: wer
30
+ value: 34.12
31
  ---
32
 
33
  # Alvenir-Wav2vec2-base-CV8-da
 
43
 
44
  | **Dataset** | **WER without LM** | **WER with 5-gram LM** |
45
  | :---: | ---: | ---: |
46
+ | [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) | 46.05 | 39.86 |
47
+ | [Alvenir test set](https://huggingface.co/datasets/Alvenir/alvenir_asr_da_eval) | 41.08 | 34.12 |