A TensorFlow implementation of Baidu's DeepSpeech architecture



Express your opinions freely and help others including your future self

Issues rank

can't download ds_ctcdecoder hot 2
Issue training existing deepspeech model using checkpoints hot 2
building libdeepspeech with deepspeech as a git submodule hot 1
Using pre trained tflite model on android hot 1
Bad audio format f or WAV hot 1
Error: Trie file version mismatch (4 instead of expected 3). Update your trie file. hot 1
Make model convertible by CoreML hot 1
InvalidArgumentError: Data too short when trying to read string hot 1
Not found: Op type not registered 'AudioSpectrogram' in binary running on deep hot 1
tensor dimension trained models hot 1
Invalid argument: WAV data chunk 'QWDu' is too large hot 1
lm::FormatLoadException hot 1
Error running session: Not found: PruneForTargets: Some target nodes not found: initialize_state hot 1
"UnknownError: Failed to get convolution algorithm" from ./bin/ hot 1
ds_ctcdecoder 0.4.1 hot 1

contributors (According to the first 100)