fixed README.md

README.md

@@ -1,7 +1,7 @@
 ---
 language: de
 datasets:
-- common_voice (trained on 3%)
+- common_voice
 - wer
 tags:
 - audio
@@ -58,7 +58,7 @@ 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
+\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -88,31 +88,31 @@ model = Wav2Vec2ForCTC.from_pretrained("de")
 `elgeish/wav2vec2-large-xlsr-53-arabic`
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'  
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\”\�\カ\æ\無\ན\カ\臣\ѹ\…\«\»\ð\ı\„\幺\א\ב\比\ш\ע\)\ứ\в\œ\ч\+\—\ш\‚\נ\м\ń\乡\$\=\ש\ф\支\(\°\и\к\̇]'  
 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()
-\\tbatch["sentence"] = re.sub('\\\\ß', 'ss', batch["sentence"])
-\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\treturn batch
+\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+\tbatch["sentence"] = re.sub('\ß', 'ss', batch["sentence"])
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\treturn 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)
+\tinputs = 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
+\twith torch.no_grad():
+\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
-\\tpred_ids = torch.argmax(logits, dim=-1)
-\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\treturn batch
+\tpred_ids = torch.argmax(logits, dim=-1)
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)