Update README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 61.91
+         value: 46.49
 ---
 
 # Wav2Vec2-Large-XLSR-53-breton
@@ -38,7 +38,7 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset("common_voice", "es, split="test[:2%]").
+test_dataset = load_dataset("common_voice", "br", split="test[:2%]").
 
 processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-breton")
 model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-breton")
@@ -48,15 +48,15 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\\\\\\\treturn batch
+  speech_array, sampling_rate = torchaudio.load(batch["path"])
+  batch["speech"] = resampler(speech_array).squeeze().numpy()
+  return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
 
 with torch.no_grad():
-\\\\\\\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+  logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -84,37 +84,37 @@ processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-br
 model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-breton")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-\\\\\\\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\\\\\\\treturn batch
+  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+  speech_array, sampling_rate = torchaudio.load(batch["path"])
+  batch["speech"] = resampler(speech_array).squeeze().numpy()
+  return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def evaluate(batch):
-\\\\\\\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+  inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-\\\\\\\\twith torch.no_grad():
-\\\\\\\\t\\\\\\\\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+  with torch.no_grad():
+    logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
     pred_ids = torch.argmax(logits, dim=-1)
-\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\\\\\\\treturn batch
+  batch["pred_strings"] = processor.batch_decode(pred_ids)
+  return 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**: 61.91 %
+**Test Result**: 46.49 %
 
 
 ## Training