diff options
-rw-r--r-- | docs/use_cases/asr.md | 10 | ||||
-rw-r--r-- | docs/use_cases/kws.md | 10 | ||||
-rw-r--r-- | docs/use_cases/kws_asr.md | 8 | ||||
-rw-r--r-- | resources/asr/samples/another_door.wav (renamed from resources/asr/samples/anotherdoor.wav) | bin | 125004 -> 125004 bytes | |||
-rw-r--r-- | resources/asr/samples/another_engineer.wav (renamed from resources/asr/samples/anotherengineer.wav) | bin | 140844 -> 140844 bytes | |||
-rw-r--r-- | resources/asr/samples/files.md | 8 | ||||
-rw-r--r-- | resources/asr/samples/i_tell_you.wav (renamed from resources/asr/samples/itellyou.wav) | bin | 119244 -> 119244 bytes | |||
-rw-r--r-- | resources/asr/samples/testing_routine.wav (renamed from resources/asr/samples/testingroutine.wav) | bin | 100204 -> 100204 bytes | |||
-rw-r--r-- | resources/kws/samples/files.md | 4 | ||||
-rw-r--r-- | resources/kws/samples/right_left_up.wav (renamed from resources/kws/samples/rightleftup.wav) | bin | 96044 -> 96044 bytes | |||
-rw-r--r-- | resources/kws/samples/yes_no_go_stop.wav (renamed from resources/kws/samples/yesnogostop.wav) | bin | 128044 -> 128044 bytes | |||
-rw-r--r-- | resources/kws_asr/samples/files.md | 2 | ||||
-rw-r--r-- | resources/kws_asr/samples/yes_no_go_stop.wav (renamed from resources/kws_asr/samples/yesnogostop.wav) | bin | 128044 -> 128044 bytes |
13 files changed, 21 insertions, 21 deletions
diff --git a/docs/use_cases/asr.md b/docs/use_cases/asr.md index 6ae1fc1..9da2603 100644 --- a/docs/use_cases/asr.md +++ b/docs/use_cases/asr.md @@ -459,11 +459,11 @@ Choice: 5. “List” menu option prints a list of pair audio clip indexes - the original filenames embedded in the application: ```log - INFO - List of Files: - INFO - 0 => anotherdoor.wav - INFO - 1 => anotherengineer.wav - INFO - 2 => itellyou.wav - INFO - 3 => testingroutine.wav + [INFO] List of Files: + [INFO] 0 => another_door.wav + [INFO] 1 => another_engineer.wav + [INFO] 2 => i_tell_you.wav + [INFO] 3 => testing_routine.wav ``` ### Running Automatic Speech Recognition diff --git a/docs/use_cases/kws.md b/docs/use_cases/kws.md index 0147e96..10b4662 100644 --- a/docs/use_cases/kws.md +++ b/docs/use_cases/kws.md @@ -421,11 +421,11 @@ Choice: application: ```log - INFO - List of Files: - INFO - 0 => down.wav - INFO - 1 => rightleftup.wav - INFO - 2 => yes.wav - INFO - 3 => yesnogostop.wav + [INFO] List of Files: + [INFO] 0 => down.wav + [INFO] 1 => right_left_up.wav + [INFO] 2 => yes.wav + [INFO] 3 => yes_no_go_stop.wav ``` ### Running Keyword Spotting diff --git a/docs/use_cases/kws_asr.md b/docs/use_cases/kws_asr.md index 55989c7..950d576 100644 --- a/docs/use_cases/kws_asr.md +++ b/docs/use_cases/kws_asr.md @@ -519,8 +519,8 @@ Choice: 5. “List” menu option prints a list of pair ... indexes - the original filenames embedded in the application: ```log - INFO - List of Files: - INFO - 0 => yesnogostop.wav + [INFO] List of Files: + [INFO] 0 => yes_no_go_stop.wav ``` ### Running Keyword Spotting and Automatic Speech Recognition @@ -531,7 +531,7 @@ The following example illustrates application output: ```log INFO - KWS audio data window size 16000 -INFO - Running KWS inference on audio clip 0 => yesnogostop.wav +INFO - Running KWS inference on audio clip 0 => yes_no_go_stop.wav INFO - Inference 1/7 INFO - For timestamp: 0.000000 (inference #: 0); threshold: 0.900000 INFO - label @ 0: yes, score: 0.996094 @@ -559,7 +559,7 @@ INFO - NPU total cycles: 28910172 It could take several minutes to complete one inference run (average time is 2-3 minutes). -Using the input “yesnogostop.wav”, the log shows inference results for the KWS operation first, detecting the +Using the input “yes_no_go_stop.wav”, the log shows inference results for the KWS operation first, detecting the trigger word “yes“ with the stated probability score (in this case 0.99). After this, the ASR inference is run, printing the words recognized from the input sample. diff --git a/resources/asr/samples/anotherdoor.wav b/resources/asr/samples/another_door.wav Binary files differindex ee08f06..ee08f06 100644 --- a/resources/asr/samples/anotherdoor.wav +++ b/resources/asr/samples/another_door.wav diff --git a/resources/asr/samples/anotherengineer.wav b/resources/asr/samples/another_engineer.wav Binary files differindex 36faef8..36faef8 100644 --- a/resources/asr/samples/anotherengineer.wav +++ b/resources/asr/samples/another_engineer.wav diff --git a/resources/asr/samples/files.md b/resources/asr/samples/files.md index 03b988b..ecb8bfd 100644 --- a/resources/asr/samples/files.md +++ b/resources/asr/samples/files.md @@ -3,13 +3,13 @@ The sample wav audio clips provided are under Creative Commons License (Creative Commons Attribution 4.0 International Public License). The source is Librispeech ASR Corpus (http://www.openslr.org/12/)- the files were converted from flac to wav. The files used are listed here for traceability: -- testingroutine.wav (orig - 251-137823-0002.flac) +- testing_routine.wav (orig - 251-137823-0002.flac) - "This isn't part of your testing routine is it" -- anotherengineer.wav (orig - 251-137823-0003.flac) +- another_engineer.wav (orig - 251-137823-0003.flac) - "Another engineer rushed toward the door to see what was happening outside" -- anotherdoor.wav (orig - 3536-23268-0010.flac) +- another_door.wav (orig - 3536-23268-0010.flac) - "And he walked immediately out of the apartment by another door" -- itellyou.wav (orig - 251-118436-0001.flac) +- i_tell_you.wav (orig - 251-118436-0001.flac) - "I tell you it is not poison she cried" ## License diff --git a/resources/asr/samples/itellyou.wav b/resources/asr/samples/i_tell_you.wav Binary files differindex 001ce80..001ce80 100644 --- a/resources/asr/samples/itellyou.wav +++ b/resources/asr/samples/i_tell_you.wav diff --git a/resources/asr/samples/testingroutine.wav b/resources/asr/samples/testing_routine.wav Binary files differindex 0d8da6b..0d8da6b 100644 --- a/resources/asr/samples/testingroutine.wav +++ b/resources/asr/samples/testing_routine.wav diff --git a/resources/kws/samples/files.md b/resources/kws/samples/files.md index 29d42ae..685d8b7 100644 --- a/resources/kws/samples/files.md +++ b/resources/kws/samples/files.md @@ -11,7 +11,7 @@ The source is http://download.tensorflow.org/data/speech_commands_v0.02.tar.gz, └── 0a9f9af7_nohash_2.wav ``` -- rightleftup.wav +- right_left_up.wav ```tree speech_commands_v0.02 @@ -31,7 +31,7 @@ The source is http://download.tensorflow.org/data/speech_commands_v0.02.tar.gz, └── 0b40aa8e_nohash_0.wav ``` -- yesnogostop.wav +- yes_no_go_stop.wav ```tree speech_commands_v0.02 diff --git a/resources/kws/samples/rightleftup.wav b/resources/kws/samples/right_left_up.wav Binary files differindex 47551e8..47551e8 100644 --- a/resources/kws/samples/rightleftup.wav +++ b/resources/kws/samples/right_left_up.wav diff --git a/resources/kws/samples/yesnogostop.wav b/resources/kws/samples/yes_no_go_stop.wav Binary files differindex 2a2c0ac..2a2c0ac 100644 --- a/resources/kws/samples/yesnogostop.wav +++ b/resources/kws/samples/yes_no_go_stop.wav diff --git a/resources/kws_asr/samples/files.md b/resources/kws_asr/samples/files.md index 6db8d65..f883283 100644 --- a/resources/kws_asr/samples/files.md +++ b/resources/kws_asr/samples/files.md @@ -3,7 +3,7 @@ The sample wav audio clips provided are under Creative Commons License (Creative Commons Attribution 4.0 International Public License). The source is http://download.tensorflow.org/data/speech_commands_v0.02.tar.gz, in particular the files used are listed here for traceability: -- yesnogostop.wav +- yes_no_go_stop.wav ```tree speech_commands_v0.02 diff --git a/resources/kws_asr/samples/yesnogostop.wav b/resources/kws_asr/samples/yes_no_go_stop.wav Binary files differindex 2a2c0ac..2a2c0ac 100644 --- a/resources/kws_asr/samples/yesnogostop.wav +++ b/resources/kws_asr/samples/yes_no_go_stop.wav |