fix mispells

tensor2tensor/data_generators/README.md

@@ -42,7 +42,7 @@ for an example of usage.
 
 The generators should yield dictionaries with string keys and values being lists
 of {int, float, str}.  Here is a very simple generator for a data-set where
-inputs are lists of 2s with length upto 100 and targets are lists of length 1
+inputs are lists of 2s with length up to 100 and targets are lists of length 1
 with an integer denoting the length of the input list.
 
 ```

tensor2tensor/data_generators/generator_utils.py

@@ -190,7 +190,7 @@ def maybe_download(directory, filename, url):
     print()
     tf.gfile.Rename(inprogress_filepath, filepath)
     statinfo = os.stat(filepath)
-    tf.logging.info("Succesfully downloaded %s, %s bytes." % (filename,
+    tf.logging.info("Successfully downloaded %s, %s bytes." % (filename,
                                                               statinfo.st_size))
   else:
     tf.logging.info("Not downloading, file already found: %s" % filepath)
@@ -242,7 +242,7 @@ def maybe_download_from_drive(directory, filename, url):
   # Print newline to clear the carriage return from the download progress
   print()
   statinfo = os.stat(filepath)
-  tf.logging.info("Succesfully downloaded %s, %s bytes." % (filename,
+  tf.logging.info("Successfully downloaded %s, %s bytes." % (filename,
                                                             statinfo.st_size))
   return filepath
 

tensor2tensor/data_generators/problem.py

@@ -130,7 +130,7 @@ class Problem(object):
   Data generation:
     * generate_data(data_dir, tmp_dir)
         - Generate training and dev datasets into data_dir.
-        - Additonal files, e.g. vocabulary files, should also be written to
+        - Additional files, e.g. vocabulary files, should also be written to
           data_dir. Vocab files are newline-separated files with each line
           containing a token. The standard convention for the filename is to
           set it to be
@@ -515,7 +515,7 @@ def _default_hparams():
   return tf.contrib.training.HParams(
       # Use this parameter to get comparable perplexity numbers with different
       # tokenizations.  This value should be set to the ratio of the number of
-      # tokens in the test set according to the tokeization used to the number
+      # tokens in the test set according to the tokenization used to the number
       # of tokens in the test set in the "official" tokenization.  For
       # example, if we are using a word-piece based model and we want to
       # compute per-word perplexity, then we set loss_multiplier to the number