experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix instructions for micro_speech training

Browse Source 
PiperOrigin-RevId: 280759722
Change-Id: I6e4e50dfa7569613f9891636b908ba8656613a0a
This commit is contained in:
Daniel Situnayake 2019-11-15 16:28:02 -08:00 committed by TensorFlower Gardener
parent c08edd7f92
commit ad9485bd46
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorflow/lite/experimental/micro/examples/micro_speech/README.md
View File

@ -559,7 +559,7 @@ To begin training, run the following:
```
python tensorflow/tensorflow/examples/speech_commands/train.py \
--model_architecture=tiny_conv --window_stride=20 --preprocess=micro \
--wanted_words="on,off" --silence_percentage=25 --unknown_percentage=25 \
--wanted_words="yes,no" --silence_percentage=25 --unknown_percentage=25 \
--quantize=1 --verbosity=INFO --how_many_training_steps="15000,3000" \
--learning_rate="0.001,0.0001" --summaries_dir=/tmp/retrain_logs \
--data_dir=/tmp/speech_dataset --train_dir=/tmp/speech_commands_train