Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: {wer_result_on_test}
+         value: 17.22
 ---
 
 # Wav2Vec2-Large-XLSR-53-Portuguese
@@ -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):
-  \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)
 
@@ -80,45 +80,44 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "pt", split="test") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "pt", split="test")
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.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 = 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`
+processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-pt")
+model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-pt")
 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):
-\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
+    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
 
-  \tpred_ids = torch.argmax(logits, dim=-1)
-  \tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-  \treturn batch
+        pred_ids = torch.argmax(logits, dim=-1)
+        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**: XX.XX %  # TODO: write output of print here. IMPORTANT: Please remember to also replace {wer_result_on_test} at the top of with this value here. tags.
-
+**Test Result**: 17.22 % 
 
 ## Training
 
@@ -127,27 +126,29 @@ 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 \
+```
+
+Notebook containing the evaluation can be found [here](https://colab.research.google.com/drive/14e-zNK_5pm8EMY9EbeZerpHx7WsGycqG?usp=sharing).