proxectonos/Nos_ASR-wav2vec2-large-xlsr-53-gl-with-lm

language: gl license: apache-2.0 datasets:

• —openslr metrics:
• —wer
• —cer tags:
• —audio
• —automatic-speech-recognition
• —gl model-index:
• —name: Wav2Vec2-Large-XLSR-53-Galician-With-LM results:
• —task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: OpenSLR type: openslr args: gl metrics:
• —name: Test WER type: wer value: 9.10
• —name: Test CER type: cer value: 3.94
• —name: Test WER (+LM) type: wer value: 6.86
• —name: Test CER (+LM) type: cer value: 2.20
• —task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 7.0 type: mozilla-foundation/commonvoice7_0 args: gl metrics:
• —name: Test WER type: wer value: 22.12
• —name: Test CER type: cer value: 5.09
• —name: Test WER (+LM) type: wer value: 15.20
• —name: Test CER (+LM) type: cer value: 3.87

Wav2Vec2-Large-XLSR-53-Galician-With-LM

This is a copy of the model diego-fustes/wav2vec2-large-xlsr-gl with an integrated language model.

Improvement This model has been compared with the baseline (diego-fustes/wav2vec2-large-xlsr-gl) on:

• —The test subset of the Galician OpenSLR dataset (837 speech samples)
• —The test subset of the Galician Common Voice 7.0 dataset (1716 speech samples)

The results are shown in the following tables:

OpenSLR77: | Model | WER | CER | | ------------- | ------------- | ------------- | | diego-fustes/wav2vec2-large-xlsr-gl | 9.10% | 3.94% | | cmagui/wav2vec2-large-xlsr-53-galician-with-lm | 6.86% | 2.20% |

Common_voice-gl: | Model | WER | CER | | ------------- | ------------- | ------------- | | diego-fustes/wav2vec2-large-xlsr-gl | 22.12% | 5.09% | | cmagui/wav2vec2-large-xlsr-53-galician-with-lm | 15.20% | 3.87% |

Citation information

If you use this model, please cite as follows:

Magariños, Carmen; Gamallo, Pablo. 2023. NosASR-wav2vec2-large-xlsr-53-gl-with-lm. URL: https://huggingface.co/proxectonos/NosASR-wav2vec2-large-xlsr-53-gl-with-lm