Update README.md

README.md

@@ -11,7 +11,7 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: GChhablani Wav2Vec2 Large 53 Portugese
+- name: Wav2Vec2 Large 53 Portugese by Gunjan Chhablani
   results:
   - task: 
       name: Speech Recognition
@@ -51,15 +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):
-  	speech_array, sampling_rate = torchaudio.load(batch["path"])
-  	batch["speech"] = resampler(speech_array).squeeze().numpy()
-  	return 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():
-  	logits = 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)
 
@@ -87,30 +87,30 @@ processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-pt
 model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-pt") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
 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):
-	  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
+\t  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+\t\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):
-  	inputs = 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)
 
-  	with torch.no_grad():
-  		logits = 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)
-  	batch["pred_strings"] = processor.batch_decode(pred_ids)
-  	return 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)
 
@@ -127,27 +127,27 @@ The Common Voice `train` and `validation` datasets were used for training. The s
 
 ```bash
 #!/usr/bin/env bash
-python run_common_voice.py \
-    --model_name_or_path="facebook/wav2vec2-large-xlsr-53" \
-    --dataset_config_name="pt" \
-    --output_dir=/workspace/output_models/pt/wav2vec2-large-xlsr-pt \
-    --cache_dir=/workspace/data \
-    --overwrite_output_dir \
-    --num_train_epochs="30" \
-    --per_device_train_batch_size="32" \
-    --per_device_eval_batch_size="32" \
-    --evaluation_strategy="steps" \
-    --learning_rate="3e-4" \
-    --warmup_steps="500" \
-    --fp16 \
-    --freeze_feature_extractor \
-    --save_steps="500" \
-    --eval_steps="500" \
-    --save_total_limit="1" \
-    --logging_steps="500" \
-    --group_by_length \
-    --feat_proj_dropout="0.0" \
-    --layerdrop="0.1" \
-    --gradient_checkpointing \
-    --do_train --do_eval \
+python run_common_voice.py \\
+    --model_name_or_path="facebook/wav2vec2-large-xlsr-53" \\
+    --dataset_config_name="pt" \\
+    --output_dir=/workspace/output_models/pt/wav2vec2-large-xlsr-pt \\
+    --cache_dir=/workspace/data \\
+    --overwrite_output_dir \\
+    --num_train_epochs="30" \\
+    --per_device_train_batch_size="32" \\
+    --per_device_eval_batch_size="32" \\
+    --evaluation_strategy="steps" \\
+    --learning_rate="3e-4" \\
+    --warmup_steps="500" \\
+    --fp16 \\
+    --freeze_feature_extractor \\
+    --save_steps="500" \\
+    --eval_steps="500" \\
+    --save_total_limit="1" \\
+    --logging_steps="500" \\
+    --group_by_length \\
+    --feat_proj_dropout="0.0" \\
+    --layerdrop="0.1" \\
+    --gradient_checkpointing \\
+    --do_train --do_eval \\
 ```