Giters
stefanpantic
/
asr
Automatic speech recognition using neural networks
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
19
Watchers:
4
Issues:
19
Forks:
1
stefanpantic/asr Issues
dataset organization
Closed
3 years ago
Comments count
1
Implement "infer" mode
Updated
4 years ago
Save dataset sizes to "size.json"
Closed
4 years ago
Is this a mistake, about QuartzNet model layer configuration
Closed
4 years ago
Comments count
1
Fix "export" mode
Closed
4 years ago
Save training parameters to "log_dir"
Updated
4 years ago
Summaries don't use their placeholders
Closed
4 years ago
URGENT: Add batch norm nodes to trainable variables collection
Closed
4 years ago
Extend "train" function with metric calculation and logging
Closed
4 years ago
"sequence_length" parameter in "ctc_loss" shouldn't be hardcoded
Closed
4 years ago
Parameter "output_dir" is unused in "export" function
Closed
4 years ago
Implement data processing pipeline for CommonVoice dataset
Closed
4 years ago
Implement Jasper model
Closed
4 years ago
Implement "train" mode
Closed
4 years ago
Look into ONNX format for model inference
Updated
4 years ago
Implement "export" mode
Closed
4 years ago
Implement data processing pipeline for the LibriSpeech dataset
Closed
4 years ago
Implement: ctc_loss, word_error_rate, label_error_rate
Closed
4 years ago
Implement "QuartzNet" model
Closed
4 years ago