Update README.md

README.md

@@ -10,7 +10,20 @@ tags:
 - speech
 - xlsr-fine-tuning-week
 license: apache-2.0
-wer: 72.62
+model-index:
+- name: XLSR Wav2Vec2 Hindi by The AI Nerd
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice hi
+      type: common_voice
+      args: hi  
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 72.62
 ---
 
 # Wav2Vec2-Large-XLSR-53-hindi
@@ -38,15 +51,15 @@ 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)
 
@@ -74,30 +87,30 @@ processor = Wav2Vec2Processor.from_pretrained("theainerd/Wav2Vec2-large-xlsr-hin
 model = Wav2Vec2ForCTC.from_pretrained("theainerd/Wav2Vec2-large-xlsr-hindi")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'  # TODO: adapt this list to include all special characters you removed from the data
+chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]'  # TODO: adapt this list to include all special characters you removed from the data
 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
 
-\\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)