search

Elleo / gst-deepspeech

NOTE: This plugin is now deprecated in favour of the coqui-stt branch in gst-plugins-bad: https://gitlab.freedesktop.org/philn/gstreamer/-/tree/coqui-stt/subprojects/gst-plugins-bad/ext/coqui
Other
169 stars 20 forks source link

Hardcoded location to model file #6

Closed ftyers closed 6 years ago

ftyers commented 6 years ago

Model file should be user-specifiable in some way:

$ gst-launch-1.0 -m filesrc location=/tmp/0002.ogg ! decodebin ! audioconvert ! audiorate ! audioresample ! deepspeech ! fakesink
TensorFlow: v1.6.0-9-g236f83e
DeepSpeech: v0.1.1-44-gd68fde8
Warning: reading entire model file into memory. Transform model file into an mmapped graph to reduce heap usage.
2018-04-01 09:45:03.834488: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Not found: /usr/share/deepspeech/models/output_graph.pb; El fitxer o directori no existeix
terminate called after throwing an instance of 'util::ErrnoException'
  what():  native_client/kenlm/util/file.cc:76 in int util::OpenReadOrThrow(const char*) threw ErrnoException because `-1 == (ret = open(name, 00))'.
El fitxer o directori no existeix while opening /usr/share/deepspeech/models/lm.binary
Avortat
Elleo commented 6 years ago

Those are configurable through the plugin properties, e.g.

... ! deepspeech ​​speech-model=/path/to/your/model ! ...

To see a list of all the available properties and their descriptions just run:

gst-inspect deepspeech