-
Is it possible to modify the resulting translated text before it's transformed to audio?
I want to S2ST with expressions, but if the translation doesn't quite match the context or whatever, to "for…
ra100 updated
1 month ago
-
Great job on implementing paper!
Question: why did you use python_speech_features.fbank instead of librosa.feature.melspectrogram ?
Both transformations are the same, right?
-
Thank you for you work, but when I try the example of Keyword Spotting，there is a bug:
, I got this issue:
File "/tango/train.py", line 553, in
…
-
```
filenames: ['aaaa']
Finished the feature extracting (12921856, 2)
0%| | 0/174 [00:00
-
```
nnet3-latgen-faster
--frame-subsampling-factor=3
--frames-per-chunk=50
--extra-left-context=0
--extra-right-context=0
--extra-left-context-initial=-1
--extra-right-context-final=-1
-…
-
thanks for the demo of your team on-going research, from the issue of other classmate, I find the two papers you refer is same with me, I have some confused question in reproducing the code in the pae…
-
Hi I tested timit data using eesen, but the result is not good as follows:
# training process
```
EPOCH 11 RUNNING ... ENDS [2016-Jun-6 17:02:47]: lrate 4e-05, TRAIN ACCURACY 23.4300%, VALID ACCURACY…
-
Refine current code
- [x] remove abundant files
- [x] modulization (e.g., mel layer, mfcc, fbank,, vocoder (world))
- [x] normalization (norm, collect stats)
- [x] make "egs", make separate d…
-
Hello,
I am trying to run the TensorFlow based EESEN setup for Switchboard. More specifically, I am using the `tf_clean` branch and trying to run the `asr_egs/swbd/v1-tf/run_ctc_char.sh` script. I am…