Create README.md

README.md

@@ -1,7 +1,8 @@
----
-language: sv
+language: {sv-SE} 
 datasets:
-- common_voice
+- common_voice 
+metrics:
+- wer
 tags:
 - audio
 - automatic-speech-recognition
@@ -9,24 +10,23 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: XLSR Wav2Vec2 Swedish by Medhi
+- name: {MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish} 
   results:
   - task: 
       name: Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice sv-SE
+      name: Common Voice {sv-SE}
       type: common_voice
-      args: sv-SE 
+      args: {sv-SE}
     metrics:
        - name: Test WER
          type: wer
-         value: ???
+         value: {41.388337}
 ---
 
-# Wav2Vec2-Large-XLSR-53-Hungarian
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Swedish using the [Common Voice](https://huggingface.co/datasets/common_voice)
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on {Swedish} 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
@@ -39,10 +39,10 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset("common_voice", "sv-SE", split="test[:2%]").
+test_dataset = load_dataset("common_voice", "{sv-SE}", split="test[:2%]") 
 
-processor = Wav2Vec2Processor.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")
-model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")
+processor = Wav2Vec2Processor.from_pretrained("{MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish}") 
+model = Wav2Vec2ForCTC.from_pretrained("{MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish}") 
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -68,7 +68,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the Swedish test data of Common Voice.
+The model can be evaluated as follows on the {Swedish} test data of Common Voice. 
 
 
 ```python
@@ -78,14 +78,14 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "sv-SE", split="test")
+test_dataset = load_dataset("common_voice", "{sv-SE}", split="test") 
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")
-model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")
+processor = Wav2Vec2Processor.from_pretrained("{MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish}")
+model = Wav2Vec2ForCTC.from_pretrained("{MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish}") 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]' 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -105,8 +105,8 @@ def evaluate(batch):
 
 	with torch.no_grad():
 		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
-    pred_ids = torch.argmax(logits, dim=-1)
-    
+
+	pred_ids = torch.argmax(logits, dim=-1)
 	batch["pred_strings"] = processor.batch_decode(pred_ids)
 	return batch
 
@@ -115,10 +115,10 @@ 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**: ???
+**Test Result**: 41.388337 %  
 
 
 ## Training
 
-The Common Voice `train` and `validation` datasets were used for training.
-The script used for training can be found ???
+The Common Voice `train`, `validation`
+