diff --git a/README.md b/README.md
index 9cab6a4..d30f90d 100644
--- a/README.md
+++ b/README.md
@@ -53,7 +53,7 @@ to resample audios to 16kHz and for some other preperations.
 
 Second, [Montreal Forced Aligner](https://montreal-forced-aligner.readthedocs.io/en/latest/) (MFA) is used to obtain the alignments between the utterances and the phoneme sequences.
 ```bash
-./montreal-forced-aligner/bin/mfa_align dataset/wav16/ lexicon/librispeech-lexicon.txt  english datset/TextGrid/ -j 10 -v
+./montreal-forced-aligner/bin/mfa_align dataset/wav16/ lexicon/librispeech-lexicon.txt  english dataset/TextGrid/ -j 10 -v
 ```
 
 Third, preprocess the dataset to prepare mel-spectrogram, duration, pitch and energy for fast training.
@@ -79,4 +79,4 @@ We refered to
 * [FastSpeech2](https://arxiv.org/abs/2006.04558)
 * [ming024's FastSpeech implementation](https://github.com/ming024/FastSpeech2)
 * [Mellotron](https://github.com/NVIDIA/mellotron)
-* [Tacotron](https://github.com/keithito/tacotron)
\ No newline at end of file
+* [Tacotron](https://github.com/keithito/tacotron)