眼見 Python Pocketsphinx 之預設組構︰
If you don’t pass any argument while creating an instance of the Pocketsphinx, AudioFile or LiveSpeech class, it will use next default values:
verbose = False logfn = /dev/null or nul audio_file = site-packages/pocketsphinx/data/goforward.raw audio_device = None sampling_rate = 16000 buffer_size = 2048 no_search = False full_utt = False hmm = site-packages/pocketsphinx/model/en-us lm = site-packages/pocketsphinx/model/en-us.lm.bin dict = site-packages/pocketsphinx/model/cmudict-en-us.dict
Any other option must be passed into the config as is, without using symbol -.
If you want to disable default language model or dictionary, you can change the value of the corresponding options to False:
lm = False dict = False
……
道明其語音檔格式原始乎？
Raw audio format
RAW Audio format or just RAW Audio is an audio file format for storing uncompressed audio in raw form. Comparable to WAV or AIFF in size, RAW Audio file does not include any header information (sampling rate, bit depth, endian, or number of channels). Data can be written in PCM, IEEE 754 or ASCII.
Extensions
Raw files can have a wide range of file extensions, common ones being .raw, .pcm, or .sam. They can also have no extension.
Playing
As there is no header, compatible audio players require information from the user that would normally be stored in a header, such as the encoding, sample rate, number of bits used per sample, and the number of channels.
………
該怎樣以『檔案為介面』界接 librosa 耶？！
一時想起☆
Advanced I/O Use Cases
This section covers advanced use cases for input and output which go beyond the I/O functionality currently provided by librosa.
Read specific formats
librosa uses audioread for reading audio. While we chose this library for best flexibility and support of various compressed formats like MP3: some specific formats might not be supported. Especially specific WAV subformats like 24bit PCM or 32bit float might cause problems depending on your installed audioread codecs. libsndfile covers a bunch of these formats. There is a neat wrapper for libsndfile called PySoundFile which makes it easy to use the library from python.
Note
See installation instruction for PySoundFile here.
Reading audio files using PySoundFile is similmar to the method in librosa. One important difference is that the read data is of shape (nb_samples, nb_channels) compared to (nb_channels, nb_samples) in <librosa.core.load>. Also the signal is not resampled to 22050 Hz by default, hence it would need be transposed and resampled for further processing in librosa. The following example is equivalent to librosa.load(librosa.util.example_audio_file()):
import librosa import soundfile as sf # Get example audio file filename = librosa.util.example_audio_file() data, samplerate = sf.read(filename, dtype='float32') data = data.T data_22k = librosa.resample(data, samplerate, 22050)
───
何不直搗黃龍
PySoundFile
PySoundFile is an audio library based on libsndfile, CFFI and NumPy. Full documentation is available on http://pysoundfile.readthedocs.org/.
PySoundFile can read and write sound files. File reading/writing is supported through libsndfile, which is a free, cross-platform, open-source (LGPL) library for reading and writing many different sampled sound file formats that runs on many platforms including Windows, OS X, and Unix. It is accessed through CFFI, which is a foreign function interface for Python calling C code. CFFI is supported for CPython 2.6+, 3.x and PyPy 2.0+. PySoundFile represents audio data as NumPy arrays.
───
一探究竟呢◎
Return a dictionary of available major formats.
Examples
In [1]: import soundfile as sf
In [2]: sf.available_formats()
Out[2]:
{'AIFF': 'AIFF (Apple/SGI)',
'AU': 'AU (Sun/NeXT)',
'AVR': 'AVR (Audio Visual Research)',
'CAF': 'CAF (Apple Core Audio File)',
'FLAC': 'FLAC (Free Lossless Audio Codec)',
'HTK': 'HTK (HMM Tool Kit)',
'IRCAM': 'SF (Berkeley/IRCAM/CARL)',
'MAT4': 'MAT4 (GNU Octave 2.0 / Matlab 4.2)',
'MAT5': 'MAT5 (GNU Octave 2.1 / Matlab 5.0)',
'MPC2K': 'MPC (Akai MPC 2k)',
'NIST': 'WAV (NIST Sphere)',
'OGG': 'OGG (OGG Container format)',
'PAF': 'PAF (Ensoniq PARIS)',
'PVF': 'PVF (Portable Voice Format)',
'RAW': 'RAW (header-less)',
'RF64': 'RF64 (RIFF 64)',
'SD2': 'SD2 (Sound Designer II)',
'SDS': 'SDS (Midi Sample Dump Standard)',
'SVX': 'IFF (Amiga IFF/SVX8/SV16)',
'VOC': 'VOC (Creative Labs)',
'W64': 'W64 (SoundFoundry WAVE 64)',
'WAV': 'WAV (Microsoft)',
'WAVEX': 'WAVEX (Microsoft)',
'WVE': 'WVE (Psion Series 3)',
'XI': 'XI (FastTracker 2)'}
soundfile.available_subtypes(format=None)
Return a dictionary of available subtypes.
| Parameters: | format (str) – If given, only compatible subtypes are returned. |
|---|
Examples
In [3]: sf.available_subtypes('RAW')
Out[3]:
{'ALAW': 'A-Law',
'DOUBLE': '64 bit float',
'DWVW_12': '12 bit DWVW',
'DWVW_16': '16 bit DWVW',
'DWVW_24': '24 bit DWVW',
'FLOAT': '32 bit float',
'GSM610': 'GSM 6.10',
'PCM_16': 'Signed 16 bit PCM',
'PCM_24': 'Signed 24 bit PCM',
'PCM_32': 'Signed 32 bit PCM',
'PCM_S8': 'Signed 8 bit PCM',
'PCM_U8': 'Unsigned 8 bit PCM',
'ULAW': 'U-Law',
'VOX_ADPCM': 'VOX ADPCM'}
soundfile.check_format(format, subtype=None, endian=None)
Check if the combination of format/subtype/endian is valid.
Examples
In [4]: sf.check_format('RAW', 'PCM_16')
Out[4]: True
soundfile.default_subtype(format)
Return the default subtype for a given format.
Examples
In [5]: sf.default_subtype('RAW')
In [6]:
雖不免波折★
soundfile.info(file, verbose=False)
Returns an object with information about a SoundFile.
| Parameters: | verbose (bool) – Whether to print additional information. |
|---|
Return a dictionary of available major formats.
Examples
In [6]: sf.info('./test/goforward.RAW')
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-6-9b0cdef67ec7> in <module>()
----> 1 sf.info('./test/goforward.RAW')
/usr/local/lib/python3.5/dist-packages/soundfile.py in info(file, verbose)
550 Whether to print additional information.
551 """
--> 552 return _SoundFileInfo(file, verbose)
553
554
/usr/local/lib/python3.5/dist-packages/soundfile.py in __init__(self, file, verbose)
497 def __init__(self, file, verbose):
498 self.verbose = verbose
--> 499 with SoundFile(file) as f:
500 self.name = f.name
501 self.samplerate = f.samplerate
/usr/local/lib/python3.5/dist-packages/soundfile.py in __init__(self, file, mode, samplerate, channels, subtype, endian, format, closefd)
737 self._mode = mode
738 self._info = _create_info_struct(file, mode, samplerate, channels,
--> 739 format, subtype, endian)
740 self._file = self._open(file, mode_int, closefd)
741 if set(mode).issuperset('r+') and self.seekable():
/usr/local/lib/python3.5/dist-packages/soundfile.py in _create_info_struct(file, mode, samplerate, channels, format, subtype, endian)
1520 if 'r' not in mode or format.upper() == 'RAW':
1521 if samplerate is None:
-> 1522 raise TypeError("samplerate must be specified")
1523 info.samplerate = samplerate
1524 if channels is None:
TypeError: samplerate must be specified
恰逢即將『狗來富』之時
RAW Files
Pysoundfile can usually auto-detect the file type of sound files. This is not possible for RAW files, though:
Pysoundfile can usually auto-detect the file type of sound files. This is not possible for RAW files, though:
In [7]: data, samplerate = sf.read('./test/goforward.RAW', channels=1, samplerate=16000, subtype='PCM_16')
Note that on x86, this defaults to endian='LITTLE'. If you are reading big endian data (mostly old PowerPC/6800-based files), you have to set endian='BIG' accordingly.
You can write RAW files in a similar way, but be advised that in most cases, a more expressive format is better and should be used instead.
pip install --upgrade pocketsphinx![apt-cache show pocketsphinx Package: pocketsphinx Version: 0.8+5prealpha-2 Architecture: armhf Maintainer: Debian Accessibility Team <debian-accessibility@lists.debian.org> Installed-Size: 8667 Depends: libc6 (>= 2.4), libpocketsphinx3, libsphinxbase3, libjs-jquery Multi-Arch: foreign Homepage: http://cmusphinx.sourceforge.net/ Priority: extra Section: sound Filename: pool/main/p/pocketsphinx/pocketsphinx_0.8+5prealpha-2_armhf.deb Size: 508836 SHA256: feeca4c0385a2fd5274ce21f9f3153bd217bbab1d1001174cea6bab8f54080fd SHA1: 0fd4274deae8e8d3cc03bd1e7045cc6ad868f91b MD5sum: 72894950089cb773826e6e90b9c94850 Description: Speech recognition tool CMU Sphinx is a large vocabulary, speaker-independent continuous speech recognition engine. . This package contains end-user speech recognition tools. Description-md5: 17fb8ee80efcb04aa65b542b1b312aa2 </pre> <span style="color: #666699;">故此不講該程式庫用法及測試也。僅借其範例控制文本︰</span> <span style="color: #808080;">How are you today</span> <span style="color: #808080;">Good morning</span> <span style="color: #808080;">night</span> <span style="color: #808080;">afternoon</span> <span style="color: #666699;">來趟工具之旅吧！</span> <span style="color: #666699;">上傳文本︰</span> <h1><span style="font-size: 14pt;"><img class="alignnone wp-image-81258" src="http://www.freesandal.org/wp-content/uploads/Sphinx-plate.png" alt="" width="81" height="80" /> <span style="color: #ff9900;"><a style="color: #ff9900;" href="http://www.speech.cs.cmu.edu/tools/lmtool-new.html">Sphinx Knowledge Base Tool -- VERSION 3</a></span></span></h1> <table border="1" cellpadding="10"> <tbody> <tr> <td> <h3><span style="color: #808080;">This is the new version of the <a style="color: #808080;" href="http://www.speech.cs.cmu.edu/tools/lmtool.html">lmtool</a>! <a style="color: #808080;" href="http://www.speech.cs.cmu.edu/tools/FAQ.html">FAQ</a></span></h3> <h4><span style="color: #808080;">Changes should be transparent (unless you automate, see note below).</span> <span style="color: #808080;"> Problems? Please help by sending a report to the maintainer.</span></h4> </td> </tr> <tr> <td><span style="color: #808080;"><b>New!</b> Follow us on <tt>@CMUSpeechGroup</tt> for announcements and status updates.</span></td> </tr> </tbody> </table> <span style="color: #ff9900;"><b> What it does:</b> Builds a consistent set of lexical and language modeling files for Sphinx (and compatible) decoders.</span> <span style="color: #ff9900;"> <b>Note:</b> If you just need pronunciations, use the <a style="color: #ff9900;" href="http://www.speech.cs.cmu.edu/tools/lextool.html">lextool</a> instead.</span> <span style="color: #ff0000;"><b>To use:</b> Create a sentence corpus file, consisting of all sentences you would like the decoder to recognize. The sentences should be one to a line (but do not need to have standard punctuation). You may not need to exhastively list all possible sentences: the decoder will allow fragments to recombine into new sentences.</span> <form action="http://www.speech.cs.cmu.edu/cgi-bin/tools/lmtool/run" enctype="multipart/form-data" method="POST"><span style="color: #808080;"><b>Upload a sentence corpus file</b>:</span> <input name="corpus" size="60" type="FILE" value="empty" /></form> <span style="color: #339966;">The <strong>new version of lmtool</strong> has been reorganized internally to make use of the <a style="color: #339966;" href="http://svn.code.sf.net/p/cmusphinx/code/trunk/logios/">Logios</a><a style="color: #339966;"> package. This will make lmtool easier to maintain in the future and will allow it to take advantage of ongoing development in Logios. These changes should be transparent to regular users. Please give it a try. If you have any problems, or discover bugs, let the maintainer know. If things look good (i.e., I stop getting bug reports) this will become the standard version. </a></span> <span style="color: #808080;"><strong>NOTE:</strong> If you have automated the use of this tool you will need to update your code. The main difference is that the name of the target script has changed. The old script will still be available so nothing will break immediately, but it's unlikely to continue to be maintained. Also, file links are no longer tagged in the html. Please let me know if you make use of this feature and I'll find a fix.</span> <span style="color: #808080;">……</span> <h1><span style="color: #ff9900;"><a style="color: #ff9900;" href="http://www.speech.cs.cmu.edu/tools/product/1517214435_23951/">Sphinx knowledge base generator [lmtool.3a]</a></span></h1> <hr /> <span style="color: #808080;">Your Sphinx knowledge base compilation has been successfully processed!</span> <span style="color: #808080;">The base name for this set is <b>2029</b>. <a style="color: #808080;" href="http://www.speech.cs.cmu.edu/tools/product/1517214435_23951/TAR2029.tgz">TAR2029.tgz</a> is the compressed version.</span> <span style="color: #808080;"> Note that this set of files is internally consistent and is best used together.</span> <span style="color: #808080;"><strong>IMPORTANT:</strong> Please download these files as soon as possible; they will be deleted in approximately a half hour.</span> <table border="1" cellspacing="0" cellpadding="10"> <tbody> <tr align="TOP"> <td> <pre>SESSION 1517214435_23951 [_INFO_] Found corpus: 4 sentences, 8 unique words [_INFO_] Found 0 words in extras (0) [_INFO_] Language model completed (0) [_INFO_] Pronounce completed (0) [_STAT_] Elapsed time: 0.007 sec</pre> Please include these messages in bug reports.</td> </tr> </tbody> </table> <span style="color: #808080;">………</span> <span style="color: #666699;">取回產生檔︰</span> <span style="color: #808080;">wget http://www.speech.cs.cmu.edu/tools/product/1517214435_23951/TAR2029.tgz</span> <pre class="lang:default decode:true">pi@raspberrypi:~/test](http://www.freesandal.org/wp-content/ql-cache/quicklatex.com-7875e5d362c576f11496f7fa464626d1_l3.png "Rendered by QuickLaTeX.com")
tar -zxvf TAR2029.tgz
2029.dic
2029.lm
2029.log_pronounce
2029.sent
2029.vocab
![pocketsphinx_continuous -adcdev plughw:1,0 -lm ./test/2029.lm -dict ./test/2029.dic -inmic yes INFO: pocketsphinx.c(145): Parsed model-specific feature parameters from /usr/share/pocketsphinx/model/en-us/en-us/feat.params Current configuration: [NAME] [DEFLT] [VALUE] -agc none none -agcthresh 2.0 2.000000e+00 -allphone -allphone_ci no no -alpha 0.97 9.700000e-01 -ascale 20.0 2.000000e+01 -aw 1 1 -backtrace no no -beam 1e-48 1.000000e-48 -bestpath yes yes -bestpathlw 9.5 9.500000e+00 -ceplen 13 13 -cmn current current -cmninit 8.0 40,3,-1 -compallsen no no -debug 0 -dict ./test/2029.dic -dictcase no no -dither no no -doublebw no no -ds 1 1 -fdict /usr/share/pocketsphinx/model/en-us/en-us/noisedict -feat 1s_c_d_dd 1s_c_d_dd -featparams /usr/share/pocketsphinx/model/en-us/en-us/feat.params -fillprob 1e-8 1.000000e-08 -frate 100 100 -fsg -fsgusealtpron yes yes -fsgusefiller yes yes -fwdflat yes yes -fwdflatbeam 1e-64 1.000000e-64 -fwdflatefwid 4 4 -fwdflatlw 8.5 8.500000e+00 -fwdflatsfwin 25 25 -fwdflatwbeam 7e-29 7.000000e-29 -fwdtree yes yes -hmm /usr/share/pocketsphinx/model/en-us/en-us -input_endian little little -jsgf -keyphrase -kws -kws_delay 10 10 -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lifter 0 22 -lm ./test/2029.lm -lmctl -lmname -logbase 1.0001 1.000100e+00 -logfn -logspec no no -lowerf 133.33334 1.300000e+02 -lpbeam 1e-40 1.000000e-40 -lponlybeam 7e-29 7.000000e-29 -lw 6.5 6.500000e+00 -maxhmmpf 30000 30000 -maxwpf -1 -1 -mdef /usr/share/pocketsphinx/model/en-us/en-us/mdef -mean /usr/share/pocketsphinx/model/en-us/en-us/means -mfclogdir -min_endfr 0 0 -mixw -mixwfloor 0.0000001 1.000000e-07 -mllr -mmap yes yes -ncep 13 13 -nfft 512 512 -nfilt 40 25 -nwpen 1.0 1.000000e+00 -pbeam 1e-48 1.000000e-48 -pip 1.0 1.000000e+00 -pl_beam 1e-10 1.000000e-10 -pl_pbeam 1e-10 1.000000e-10 -pl_pip 1.0 1.000000e+00 -pl_weight 3.0 3.000000e+00 -pl_window 5 5 -rawlogdir -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -samprate 16000 1.600000e+04 -seed -1 -1 -sendump /usr/share/pocketsphinx/model/en-us/en-us/sendump -senlogdir -senmgau -silprob 0.005 5.000000e-03 -smoothspec no no -svspec 0-12/13-25/26-38 -tmat /usr/share/pocketsphinx/model/en-us/en-us/transition_matrices -tmatfloor 0.0001 1.000000e-04 -topn 4 4 -topn_beam 0 0 -toprule -transform legacy dct -unit_area yes yes -upperf 6855.4976 6.800000e+03 -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 20 20 -vad_startspeech 10 10 -vad_threshold 2.0 2.000000e+00 -var /usr/share/pocketsphinx/model/en-us/en-us/variances -varfloor 0.0001 1.000000e-04 -varnorm no no -verbose no no -warp_params -warp_type inverse_linear inverse_linear -wbeam 7e-29 7.000000e-29 -wip 0.65 6.500000e-01 -wlen 0.025625 2.562500e-02 INFO: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none' INFO: cmn.c(143): mean[0]= 12.00, mean[1..12]= 0.0 INFO: acmod.c(164): Using subvector specification 0-12/13-25/26-38 INFO: mdef.c(518): Reading model definition: /usr/share/pocketsphinx/model/en-us/en-us/mdef INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef file INFO: bin_mdef.c(336): Reading binary model definition: /usr/share/pocketsphinx/model/en-us/en-us/mdef INFO: bin_mdef.c(516): 42 CI-phone, 137053 CD-phone, 3 emitstate/phone, 126 CI-sen, 5126 Sen, 29324 Sen-Seq INFO: tmat.c(206): Reading HMM transition probability matrices: /usr/share/pocketsphinx/model/en-us/en-us/transition_matrices INFO: acmod.c(117): Attempting to use PTM computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/share/pocketsphinx/model/en-us/en-us/means INFO: ms_gauden.c(292): 42 codebook, 3 feature, size: INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/share/pocketsphinx/model/en-us/en-us/variances INFO: ms_gauden.c(292): 42 codebook, 3 feature, size: INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(294): 128x13 INFO: ms_gauden.c(354): 222 variance values floored INFO: ptm_mgau.c(476): Loading senones from dump file /usr/share/pocketsphinx/model/en-us/en-us/sendump INFO: ptm_mgau.c(500): BEGIN FILE FORMAT DESCRIPTION INFO: ptm_mgau.c(563): Rows: 128, Columns: 5126 INFO: ptm_mgau.c(595): Using memory-mapped I/O for senones INFO: ptm_mgau.c(835): Maximum top-N: 4 INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0 INFO: dict.c(320): Allocating 4112 * 20 bytes (80 KiB) for word entries INFO: dict.c(333): Reading main dictionary: ./test/2029.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 11 words read INFO: dict.c(358): Reading filler dictionary: /usr/share/pocketsphinx/model/en-us/en-us/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(361): 5 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 42^3 * 2 bytes (144 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 21336 bytes (20 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 21336 bytes (20 KiB) for single-phone word triphones INFO: ngram_model_trie.c(456): Trying to read LM in trie binary format INFO: ngram_model_trie.c(467): Header doesn't match INFO: ngram_model_trie.c(189): Trying to read LM in arpa format INFO: ngram_model_trie.c(205): LM of order 3 INFO: ngram_model_trie.c(207): #1-grams: 10 INFO: ngram_model_trie.c(207): #2-grams: 12 INFO: ngram_model_trie.c(207): #3-grams: 8 INFO: lm_trie.c(399): Training quantizer INFO: lm_trie.c(407): Building LM trie INFO: ngram_search_fwdtree.c(99): 10 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 7 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 7 single-phone words INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 144 INFO: ngram_search_fwdtree.c(339): after: 10 root, 16 non-root channels, 6 single-phone words INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25 INFO: continuous.c(305): pocketsphinx_continuous COMPILED ON: May 22 2016, AT: 22:01:16 READY.... Listening... INFO: cmn_prior.c(131): cmn_prior_update: from < 49.97 1.81 -0.92 -14.74 13.21 -4.28 4.37 -9.02 0.91 -0.52 1.94 6.10 5.16 > INFO: cmn_prior.c(149): cmn_prior_update: to < 51.51 4.53 -0.17 -16.11 16.84 -6.16 3.78 -7.40 2.23 -2.91 2.76 3.19 3.94 > INFO: ngram_search_fwdtree.c(1553): 625 words recognized (7/fr) INFO: ngram_search_fwdtree.c(1555): 14861 senones evaluated (177/fr) INFO: ngram_search_fwdtree.c(1559): 8554 channels searched (101/fr), 800 1st, 6824 last INFO: ngram_search_fwdtree.c(1562): 740 words for which last channels evaluated (8/fr) INFO: ngram_search_fwdtree.c(1564): 357 candidate words for entering last phone (4/fr) INFO: ngram_search_fwdtree.c(1567): fwdtree 0.27 CPU 0.321 xRT INFO: ngram_search_fwdtree.c(1570): fwdtree 1.07 wall 1.275 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 9 words INFO: ngram_search_fwdflat.c(948): 554 words recognized (7/fr) INFO: ngram_search_fwdflat.c(950): 16178 senones evaluated (193/fr) INFO: ngram_search_fwdflat.c(952): 11548 channels searched (137/fr) INFO: ngram_search_fwdflat.c(954): 946 words searched (11/fr) INFO: ngram_search_fwdflat.c(957): 477 word transitions (5/fr) INFO: ngram_search_fwdflat.c(960): fwdflat 0.16 CPU 0.190 xRT INFO: ngram_search_fwdflat.c(963): fwdflat 0.16 wall 0.194 xRT INFO: ngram_search.c(1253): lattice start node <s>.0 end node </s>.40 INFO: ngram_search.c(1279): Eliminated 0 nodes before end node INFO: ngram_search.c(1384): Lattice has 121 nodes, 127 links INFO: ps_lattice.c(1380): Bestpath score: -1785 INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:40:82) = -103465 INFO: ps_lattice.c(1441): Joint P(O,S) = -128686 P(S|O) = -25221 INFO: ngram_search.c(875): bestpath 0.01 CPU 0.012 xRT INFO: ngram_search.c(878): bestpath 0.00 wall 0.001 xRT ### NIGHT READY.... Listening... ^C pi@raspberrypi:~](http://www.freesandal.org/wp-content/ql-cache/quicklatex.com-5daa3f7f61cb2601b3620b283b68d691_l3.png "Rendered by QuickLaTeX.com")