AigizK
/

wav2vec2-large-xls-r-300m-bashkir-cv7_opt

Automatic Speech Recognition

Generated from Trainer

hf-asr-leaderboard

mozilla-foundation/common_voice_7_0

robust-speech-event

Inference Endpoints

Model card Files Files and versions Community

AigizK commited on Feb 2, 2022

Commit

e23784b

•

1 Parent(s): 31eefda

update wer info

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 9.2451
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - BA dataset.
 It achieves the following results on the evaluation set:
-- Training Loss: 0.307100
-- Validation Loss: 0.118680
-- Wer: 0.092451
 ## Model description

     metrics:
        - name: Test WER
          type: wer
+         value: 0.04688827226909791
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - BA dataset.
 It achieves the following results on the evaluation set:
+- Training Loss: 0.268400
+- Validation Loss: 0.088252
+- WER without LM: 0.085588
+- WER with LM: 0.04688827226909791
+- CER with LM: 0.01121871653232625
 ## Model description