geninhu
/

xls-asr-vi-40h-1B

Automatic Speech Recognition

hf-asr-leaderboard

robust-speech-event

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

geninhu commited on Jan 29, 2022

Commit

6a0334f

·

1 Parent(s): 60dafac

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -29,19 +29,19 @@ model-index:
 # xls-asr-vi-40h-1B
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the 40 hours of Vietnamese ASR data, including common_voice 7.0 and private dataset.
 ### Benchmark WER result:
 | | [VIVOS](https://huggingface.co/datasets/vivos) | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
 |---|---|---|
 |without LM| 25.93 | 34.21 |
-|with 4-grams LM| 0.24 | 28.27 |
 ### Benchmark CER result:
 | | [VIVOS](https://huggingface.co/datasets/vivos) | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
 |---|---|---|
 |without LM| 9.24 | 19.94 |
-|with 4-grams LM| 0.104 | 14.42 |
 ## Evaluation

 # xls-asr-vi-40h-1B
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on 40 hours of Vietnamese ASR data, including common_voice 7.0 vi and private dataset.
 ### Benchmark WER result:
 | | [VIVOS](https://huggingface.co/datasets/vivos) | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
 |---|---|---|
 |without LM| 25.93 | 34.21 |
+|with 4-grams LM| 24.11 | 28.27 |
 ### Benchmark CER result:
 | | [VIVOS](https://huggingface.co/datasets/vivos) | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
 |---|---|---|
 |without LM| 9.24 | 19.94 |
+|with 4-grams LM| 10.37 | 14.42 |
 ## Evaluation