Minor docfixes (#63)

* Update lightning.rst

* Update README.md

* Update brief_intro.rst

* Update README.md

README.md

@@ -68,7 +68,7 @@ pip install https://github.com/PyTorchLightning/metrics/archive/master.zip
 ## What is Torchmetrics
 TorchMetrics is a collection of 25+ PyTorch metrics implementations and an easy-to-use API to create custom metrics. It offers:
 
-* A standardized interface to increase reproducability
+* A standardized interface to increase reproducibility
 * Reduces Boilerplate
 * Automatic accumulation over batches
 * Metrics optimized for distributed-training
@@ -199,7 +199,7 @@ class MyAccuracy(Metric):
 
 ### Functional metrics
 
-Similar to [`torch.nn`](https://pytorch.org/docs/stable/nn.html), most metrics have both a [module-based](https://pytorchlightning.github.io/metrics/references/modules.html) and a [functional](https://pytorchlightning.github.io/metrics/references/functional.html) version.
+Similar to [`torch.nn`](https://pytorch.org/docs/stable/nn.html), most metrics have both a [module-based](https://torchmetrics.readthedocs.io/en/latest/references/modules.html) and a [functional](https://torchmetrics.readthedocs.io/en/latest/references/functional.html) version.
 The functional versions are simple python functions that as input take [torch.tensors](https://pytorch.org/docs/stable/tensors.html) and return the corresponding metric as a [torch.tensor](https://pytorch.org/docs/stable/tensors.html).
 
 ``` python

docs/source/pages/brief_intro.rst

@@ -1,7 +1,7 @@
 TorchMetrics is a collection of Machine learning metrics for distributed, scalable PyTorch models and an easy-to-use API to create custom metrics. It offers:
 
 * Optimized for distributed-training
-* A standardized interface to increase reproducability
+* A standardized interface to increase reproducibility
 * Reduces Boilerplate
 * Distrubuted-training compatible
 * Rigorously tested

docs/source/pages/lightning.rst

@@ -9,7 +9,7 @@
 TorchMetrics in PyTorch Lightning
 #################################
 
-TorchMetrics was originaly created as part of `PyTorch Lightning <https://github.com/PyTorchLightning/pytorch-lightning>`_, a pwerful deep learning research framework designed for scaling models without boilerplate.
+TorchMetrics was originaly created as part of `PyTorch Lightning <https://github.com/PyTorchLightning/pytorch-lightning>`_, a powerful deep learning research framework designed for scaling models without boilerplate.
 
 While TorchMetrics was built to be used with native PyTorch, using TorchMetrics with Lightning offers additional benefits: