buriburisuri/speech-to-text-wavenet
Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow
PythonApache-2.0
Issues
- 1
Why is the CTC losses are so high
#118 opened by minhnhatphan - 5
No module named 'version' --scikits.audiolab
#106 opened by tiankong-hut - 1
- 1
- 0
is it possible we get timestamp from this algo
#125 opened by nathphoenix - 2
- 0
Loss is inf
#124 opened by allipilli-harshitha - 1
Segmentation fault (core dumped) on recognize.py
#121 opened by igormcsouza - 0
requirements
#123 opened by marshonhuckleberry - 0
Error in recognize
#122 opened by sandeepbhutani304 - 0
why dont this program run in gpu in google colab?
#112 opened by noronet - 2
Issue predicting with pretrained model
#85 opened by jmiller656 - 2
- 2
exporting pb file
#84 opened by eli99999 - 6
- 0
input shape?
#120 opened by SibtainRazaJamali - 0
Any plans to support TF 1.13 or 2.0?
#119 opened by MaxPowerWasTaken - 0
Does WaveNet use previous frames to classify current frame?
#117 opened by SRHyd - 0
Lovely work!
#116 opened by LanceNorskog - 3
Recognise.py error
#113 opened by atanumandal0491 - 1
- 1
Problem occurs when running the train.py
#107 opened - 3
- 0
Error in Docker run
#111 opened by KonstantinosTro - 0
Missing blank space between words
#109 opened by HariWu1995 - 0
Cannot visualize model with TensorBoard
#110 opened by HariWu1995 - 1
- 0
PER accuracy of this repo
#108 opened by himat - 7
Train error: No valid path found.
#74 opened by rachel-bousfield - 0
Blank or EMP label
#105 opened by mfouadthabet - 2
ValueError: Shape must be rank 1 but is rank 0 for 'random_normal_6/RandomStandardNormal' (op: 'RandomStandardNormal') with input shapes: [].
#76 opened by R-Prady - 0
- 0
Speaker identification?
#100 opened by taewookim - 0
Run time error
#98 opened by guruvasuraj - 0
_load_mfcc not working
#96 opened by skokad - 3
Loss: inf after few Epoch
#90 opened by JulienHeiduk - 0
-
#95 opened by WKChung1028 - 0
how can i recognize my own wav file?
#93 opened by yyhlvdl - 1
recognize.py on multiple files
#81 opened by rachel-bousfield - 0
Invalid pointer in docker container
#92 opened by wielandbrendel - 0
Pre-Trained model not working
#91 opened by asad1996172 - 3
Implementing a language model
#83 opened by lightnarcissus - 1
Can I train this in a CPU machine? and what changes need to perform to train in CPU machine?
#89 opened by faruk-ahmad - 0
- 0
Desired Output
#88 opened by atanumandal0491 - 2
Docker image: scikits.audiolab missing
#78 opened by greigs - 0
- 0
TypeError: Expected labels to be a SparseTensor
#80 opened by bt9411 - 6
Training issue with divide by zero
#75 opened by rachel-bousfield - 0