lnxdx commited on
Commit
f4c3509
1 Parent(s): 92f01c2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -3
README.md CHANGED
@@ -19,7 +19,18 @@ model-index:
19
  name: Speech Recognition
20
  type: automatic-speech-recognition
21
  dataset:
22
- name: Common Voice 13.0
 
 
 
 
 
 
 
 
 
 
 
23
  type: common_voice_13_0
24
  args: fa
25
  metrics:
@@ -41,8 +52,9 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  # wav2vec2-large-xlsr-persian-asr-shemo_me7494
43
 
44
- This model is a fine-tuned version of [masoudmzb/wav2vec2-xlsr-multilingual-53-fa](https://huggingface.co/masoudmzb/wav2vec2-xlsr-multilingual-53-fa) on the None dataset.
45
- It achieves the following results on the evaluation set:
 
46
  - Loss on ShEMO train set: 0.7618
47
  - Loss on ShEMO dev set: 0.6728
48
  - WER on ShEMO train set: 30.47
 
19
  name: Speech Recognition
20
  type: automatic-speech-recognition
21
  dataset:
22
+ name: Common Voice 13.0 fa
23
+ type: common_voice_13_0
24
+ args: fa
25
+ metrics:
26
+ - name: Test WER
27
+ type: wer
28
+ value: 19.21
29
+ - task:
30
+ name: Speech Recognition
31
+ type: automatic-speech-recognition
32
+ dataset:
33
+ name: Common Voice 13.0 fa
34
  type: common_voice_13_0
35
  args: fa
36
  metrics:
 
52
 
53
  # wav2vec2-large-xlsr-persian-asr-shemo_me7494
54
 
55
+ This model is a fine-tuned version of [masoudmzb/wav2vec2-xlsr-multilingual-53-fa](https://huggingface.co/masoudmzb/wav2vec2-xlsr-multilingual-53-fa)
56
+ on the [ShEMO](https://github.com/pariajm/sharif-emotional-speech-dataset) dataset.
57
+ It achieves the following results:
58
  - Loss on ShEMO train set: 0.7618
59
  - Loss on ShEMO dev set: 0.6728
60
  - WER on ShEMO train set: 30.47