Closed cheahheng closed 4 years ago
Please, then please tell me which version of deepspeech that will be able to run the following
deepspeech --model deepspeech-0.6.1-models/output_graph.pbmm --scorer deepspeech-0.6.1-models/kenlm.scorer --audio audio/2830-3980-0043.wav
This README you refer to is for master and is correct.
The 0.6.1 README which you do not refer to is also correct and does not mention a kenlm.scorer.
When using Deep Speech 0.6.1 please refer to the 0.6.1 README
The master readme is not correct because the deepspeech-0.6.1-models that it states to download simply does not contain kenlm.scorer
This README you refer to is for master and is correct. The 0.6.1 README which you do not refer to is also correct and does not mention a kenlm.scorer. When using Deep Speech 0.6.1 please refer to the 0.6.1 README
The master readme is not correct because the deepspeech-0.6.1-models that it states to download simply does not contain kenlm.scorer
If you are using deepspeech 0.6.1 you need to refer to README of 0.6.1.
We welcome any suggestions to solve this chicken / egg problem for master, but so far we have not been able to find a valid solution.
This README you refer to is for master and is correct. The 0.6.1 README which you do not refer to is also correct and does not mention a kenlm.scorer. When using Deep Speech 0.6.1 please refer to the 0.6.1 README
The master readme is not correct because the deepspeech-0.6.1-models that it states to download simply does not contain kenlm.scorer
If you are using deepspeech 0.6.1 you need to refer to README of 0.6.1.
We welcome any suggestions to solve this chicken / egg problem for master, but so far we have not been able to find a valid solution.
@cheahheng Please see the discussion in PR #2824
Closing for lack of actionable item
This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.
This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.
The readme at deepspeech stable release ask user to download the following https://github.com/mozilla/DeepSpeech/releases/download/v0.6.1/deepspeech-0.6.1-models
And run the following $ deepspeech --model deepspeech-0.6.1-models/output_graph.pbmm --scorer deepspeech-0.6.1-models/kenlm.scorer --audio audio/2830-3980-0043.wav
However, this folder deepspeech-0.6.1-models does not contain kenlm.scorer. Also, the following $ pip3 install deepspeech
installs deepspeech version 0.6.1 which does not yet support the scorer option
Can you please make correction to the readme file found in the following path https://github.com/mozilla/DeepSpeech