diff --git a/doc/index.rst b/doc/index.rst
index 78f2f8c..d75a6b7 100644
--- a/doc/index.rst
+++ b/doc/index.rst
@@ -13,7 +13,7 @@ A short paper describing the library is available on arXiv http://arxiv.org/abs/
 
 Supported Operating Systems
 ---------------------------
-fastFM has a continous integration / testing servers (Travis) for **Linux (Ubuntu 14.04 LTS)**
+fastFM has a continuous integration / testing servers (Travis) for **Linux (Ubuntu 14.04 LTS)**
 and **OS X Mavericks**. Other OS are not actively supported.
 
 .. toctree::
diff --git a/doc/tutorial.rst b/doc/tutorial.rst
index d38762a..629eb39 100644
--- a/doc/tutorial.rst
+++ b/doc/tutorial.rst
@@ -12,7 +12,7 @@ Regression with ALS Solver
 --------------------------
 
 We first set up a small toy dataset for a regression problem. Please
-refere to [SIGIR2011] for background information on the implemented ALS solver.
+refer to [SIGIR2011] for background information on the implemented ALS solver.
 
 .. testcode::
 
diff --git a/examples/warm_start_als.py b/examples/warm_start_als.py
index e28d927..6eab47d 100644
--- a/examples/warm_start_als.py
+++ b/examples/warm_start_als.py
@@ -37,7 +37,7 @@
 
     fm = als.FMRegression(n_iter=0, l2_reg_w=l2_reg_w,
             l2_reg_V=l2_reg_V, rank=rank, random_state=seed)
-    # initalize coefs
+    # initialize coefs
     fm.fit(X_train, y_train)
 
     rmse_train = []
diff --git a/examples/warm_start_mcmc.py b/examples/warm_start_mcmc.py
index 37a5076..4aa3c45 100644
--- a/examples/warm_start_mcmc.py
+++ b/examples/warm_start_mcmc.py
@@ -48,7 +48,7 @@
     """
 
     fm = mcmc.FMRegression(n_iter=0, rank=rank, random_state=seed)
-    # initalize coefs
+    # initialize coefs
     fm.fit_predict(X_train, y_train, X_test)
 
     rmse_test = []
diff --git a/fastFM/bpr.py b/fastFM/bpr.py
index 877c483..91317fa 100644
--- a/fastFM/bpr.py
+++ b/fastFM/bpr.py
@@ -38,7 +38,7 @@ class FMRecommender(FactorizationMachine):
 
     step_size : float
         Stepsize for the SGD solver, the solver uses a fixed step size and
-        might require a tunning of the number of iterations `n_iter`.
+        might require a tuning of the number of iterations `n_iter`.
 
     Attributes
     ---------
diff --git a/fastFM/sgd.py b/fastFM/sgd.py
index 27f9810..279641d 100644
--- a/fastFM/sgd.py
+++ b/fastFM/sgd.py
@@ -41,7 +41,7 @@ class FMRegression(FactorizationMachine, RegressorMixin):
 
     step_size : float
         Stepsize for the SGD solver, the solver uses a fixed step size and
-        might require a tunning of the number of iterations `n_iter`.
+        might require a tuning of the number of iterations `n_iter`.
 
     Attributes
     ---------
@@ -125,7 +125,7 @@ class FMClassification(BaseFMClassifier):
 
     step_size : float
         Stepsize for the SGD solver, the solver uses a fixed step size and
-        might require a tunning of the number of iterations `n_iter`.
+        might require a tuning of the number of iterations `n_iter`.
 
     Attributes
     ---------
diff --git a/fastFM/tests/test_als.py b/fastFM/tests/test_als.py
index e3707a9..ab25ee0 100644
--- a/fastFM/tests/test_als.py
+++ b/fastFM/tests/test_als.py
@@ -140,7 +140,7 @@ def test_warm_start_path():
 
     fm = als.FMRegression(n_iter=0, l2_reg_w=l2_reg_w,
                           l2_reg_V=l2_reg_V, rank=rank, random_state=seed)
-    # initalize coefs
+    # initialize coefs
     fm.fit(X_train, y_train)
 
     rmse_train = []
diff --git a/fastFM/validation.py b/fastFM/validation.py
index ebc5330..160c184 100644
--- a/fastFM/validation.py
+++ b/fastFM/validation.py
@@ -217,7 +217,7 @@ def check_random_state(seed):
 
 
 def _shape_repr(shape):
-    """Return a platform independent reprensentation of an array shape
+    """Return a platform independent representation of an array shape
     Under Python 2, the `long` type introduces an 'L' suffix when using the
     default %r format for tuples of integers (typically used to store the shape
     of an array).