Deep Speech


About the Deep Speech category (1)
Help with understanding benchmarks - are we at 20% on Librespeech Clean+Other? (2)
Is it OK if all jobs are on worker:0? (2)
Unexpected ResourceExhaustedError (14)
Creating an Indian accent model with ~115k files (12)
How could I apply transfer learning on pre trained model? (1)
Distributed training (8)
Error during trie creation ( 2 3 ) (58)
TUTORIAL : How I trained a specific french model to control my robot ( 2 3 4 ) (65)
Does anyone got a good result when training the Common Voice data set? (4)
Unable to run inference on trained model (2)
Distributed training set up of DeepSpeech code (5)
Any documentation around the tensorboard outputs? (2)
How exactly the decoder (and especially tf.nn.ctc_beam_search_decoder) works? (10)
Illegal Instruction error on Rasberry Pi (9)
Training parameters for Librispeech-clean dataset (4)
Training Chinese model (12)
Inference Model trained with DeepSpeech.py (9)
Error while running sample model on Raspbian GNU/Linux 9.4 (stretch) (6)
Custom Model created by me has a small size (1)
Decoding for proper nouns(human names) (2)
Cleaning Transcript Files (Invalid label when building trie) (13)
LSTM vs. GRU (2)
Can we use DeepSpeech for Vietnamese Speech To Text? ( 2 ) (37)
Doesn`t use GPU while training, but during recognition it uses one (20)
Can I use other language modelling tools than KenLM (8)
How to modify this code to output multi-candidate results by beam search? (1)
Training Common Voice issue: Invalid argument: Labels length is zero in batch 0 (9)
Produce lattices or n-bests instead of just one best (3)
Training issues and completion time (1)