Update README.md

README.md

@@ -2,8 +2,6 @@
 language: mn
 datasets:
 - common_voice
-metrics:
-- wer
 tags:
 - audio
 - automatic-speech-recognition
@@ -11,15 +9,15 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: bayartsogt/wav2vec2-large-xlsr-mongolian
-results:
+- name: XLSR Wav2Vec2 Mongolian by Bayartsogt
+  results:
   - task: 
       name: Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice mn-MN
+      name: Common Voice mn
       type: common_voice
-      args: mn
+      args: mn  
     metrics:
        - name: Test WER
          type: wer
@@ -51,15 +49,15 @@ 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
+\\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)
 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)
 
@@ -86,31 +84,31 @@ processor = Wav2Vec2Processor.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mo
 model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\'h\\«\\»]'
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\'h\\\\«\\\\»]'
 
 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
+\\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
 
 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
 
     pred_ids = torch.argmax(logits, dim=-1)
-\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\treturn batch
+\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)