Copy breton2 to breton

README.md

@@ -21,9 +21,9 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 44.34
+         value: 43.43
 ---
-# Wav2Vec2-Large-XLSR-53-Breton
+# wav2vec2-large-xlsr-53-breton2
 The model can be used directly (without a language model) as follows:
 ```python
 import torch
@@ -34,8 +34,8 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 lang = "br"
 test_dataset = load_dataset("common_voice", lang, split="test[:2%]") 
 
-processor = Wav2Vec2Processor.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton") 
-model = Wav2Vec2ForCTC.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton")
+processor = Wav2Vec2Processor.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton2") 
+model = Wav2Vec2ForCTC.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton2")
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -66,16 +66,16 @@ print("Prediction:", processor.batch_decode(predicted_ids))
 print("Reference:", test_dataset["sentence"][:nb_samples])
 ```
 The above code leads to the following prediction for the first two samples:
-* Prediction: ["nel ler ket dont abenn eus netra la vez ser mirc'hid evel sij", 'an eil hag egile']
-* Reference: ["N'haller ket dont a-benn eus netra pa vezer nec'het evel-se ", 'An eil hag egile ']
+* Prediction: ["neller ket dont a-benn eus netra la vez ser merc'hed evel sich", 'an eil hag egile']
+* Reference: ["N'haller ket dont a-benn eus netra pa vezer nec'het evel-se.", 'An eil hag egile.']
 
 The model can be evaluated as follows on the {language} test data of Common Voice.
 ```python
+import re
 import torch
 import torchaudio
 from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-import re
 
 lang = 'br'
 test_dataset = load_dataset("common_voice", lang, split="test")
@@ -120,4 +120,8 @@ def evaluate(batch):
 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**: 43.43%
+## Training
+The Common Voice `train`, `validation` datasets were used for training.