Merge branch 'main' of https://huggingface.co/not-tanh/wav2vec2-large-xlsr-53-vietnamese into main

README.md

@@ -24,12 +24,12 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 52.486188
+         value: 40.745856
 ---
 
-# Wav2Vec2-Large-XLSR-53-vietnamese #TODO: replace language with your {language}, *e.g.* French
+# Wav2Vec2-Large-XLSR-53-Vietnamese
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Vietnamese using the [Common Voice](https://huggingface.co/datasets/common_voice), and [Vivos dataset](https://ailab.hcmus.edu.vn/vivos).
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Vietnamese using the [Common Voice](https://huggingface.co/datasets/common_voice), [Vivos dataset](https://ailab.hcmus.edu.vn/vivos) and [FOSD dataset](https://data.mendeley.com/datasets/k9sxg2twv4/4).
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Usage
@@ -42,10 +42,10 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset("common_voice", "vi", split="test") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "vi", split="test")
 
-processor = Wav2Vec2Processor.from_pretrained("{model_id}") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
-model = Wav2Vec2ForCTC.from_pretrained("{model_id}") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
+processor = Wav2Vec2Processor.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
+model = Wav2Vec2ForCTC.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -71,7 +71,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
+The model can be evaluated as follows on the Vietnamese test data of Common Voice.
 
 
 ```python
@@ -88,7 +88,7 @@ processor = Wav2Vec2Processor.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-v
 model = Wav2Vec2ForCTC.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“%\\\\'�]'
+chars_to_ignore_regex = r'[,?.!\-;:"“%\'�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -118,12 +118,12 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 
-**Test Result**: 52.486188%
+**Test Result**: 40.745856%
 
 
 ## Training
 ## TODO
 
-The Common Voice `train`, `validation`, and `vivos` datasets were used for training
+The Common Voice `train`, `validation`, the VIVOS and FOSD datasets were used for training
 
-The script used for training can be found ... # TODO: fill in a link to your training script here. If you trained your model in a colab, simply fill in the link here. If you trained the model locally, it would be great if you could upload the training script on github and paste the link here.
+The script used for training can be found ... # TODO