Update README.md

README.md

@@ -3,60 +3,123 @@ language: mn
 datasets:
 - common_voice
 tags:
-- speech
 - audio
 - automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
 license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Mongolian by Tugstugi
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice mn
+      type: common_voice
+      args: mn  
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 42.80
 ---
 
-## Evaluation on Common Voice Mongolian Test
+# Wav2Vec2-Large-XLSR-53-Mongolian
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Mongolian using the [Common Voice](https://huggingface.co/datasets/common_voice)
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+## Usage
+
+The model can be used directly (without a language model) as follows:
+
 ```python
+import torch
 import torchaudio
-from datasets import load_dataset, load_metric
-from transformers import (
-    Wav2Vec2ForCTC,
-    Wav2Vec2Processor,
-)
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+test_dataset = load_dataset("common_voice", "mn", split="test[:2%]").
+
+processor = Wav2Vec2Processor.from_pretrained("wav2vec2-large-xlsr-53-mongolian")
+model = Wav2Vec2ForCTC.from_pretrained("wav2vec2-large-xlsr-53-mongolian")
+
+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
+
+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
+
+predicted_ids = torch.argmax(logits, dim=-1)
+
+print("Prediction:", processor.batch_decode(predicted_ids))
+print("Reference:", test_dataset["sentence"][:2])
+```
+
+
+## Evaluation
+
+The model can be evaluated as follows on the Mongolian test data of Common Voice.
+
+
+```python
 import torch
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
-import sys
 
-model_name = "tugstugi/wav2vec2-large-xlsr-53-mongolian"
-device = "cuda"
+test_dataset = load_dataset("common_voice", "mn", split="test")
+wer = load_metric("wer")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"]'  # noqa: W605
+processor = Wav2Vec2Processor.from_pretrained("wav2vec2-large-xlsr-53-mongolian")
+model = Wav2Vec2ForCTC.from_pretrained("wav2vec2-large-xlsr-53-mongolian")
+model.to("cuda")
 
-model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
-processor = Wav2Vec2Processor.from_pretrained(model_name)
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
-ds = load_dataset("common_voice", "mn", split="test", data_dir="./cv-corpus-6.1-2020-12-11")
+# 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
 
-resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)
+test_dataset = test_dataset.map(speech_file_to_array_fn)
 
-def map_to_array(batch):
-    speech, _ = torchaudio.load(batch["path"])
-    batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
-    batch["sampling_rate"] = resampler.new_freq
-    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'")
-    return batch
+# 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)
 
-ds = ds.map(map_to_array)
+	with torch.no_grad():
+		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
-def map_to_pred(batch):
-    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
-    input_values = features.input_values.to(device)
-    attention_mask = features.attention_mask.to(device)
-    with torch.no_grad():
-        logits = model(input_values, attention_mask=attention_mask).logits
     pred_ids = torch.argmax(logits, dim=-1)
-    batch["predicted"] = processor.batch_decode(pred_ids)
-    batch["target"] = batch["sentence"]
-    return batch
-
-result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys()))
+	batch["pred_strings"] = processor.batch_decode(pred_ids)
+	return batch
 
-wer = load_metric("wer")
+result = test_dataset.map(evaluate, batched=True, batch_size=8)
 
-print(wer.compute(predictions=result["predicted"], references=result["target"]))
+print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
-**Result**: 42.80 %
+
+**Test Result**: 42.80 %
+
+
+## Training
+
+The Common Voice `train`, `validation` datasets were used for training.
+
+The script used for training can be found ???