-
Currently, I'm using DeepSpeech 0.9.3 and trying to find out Word Error Rate on the Common Voice Mozilla dataset. My question is, is there any python script to find out WER? if Yes, please help me wit…
-
### CircuitPython version
```python
Adafruit CircuitPython 9.2.0 on 2024-10-28; Pimoroni Pico Plus 2 with rp2350b
```
### Code/REPL
```python
import board
import audiobusio
import audiocore
imp…
-
For support and discussions, please use our [Discourse forums](https://discourse.mozilla.org/c/deep-speech).
If you've found a bug, or have a feature request, then please create an issue with the f…
-
A [WER](https://en.m.wikipedia.org/wiki/Word_error_rate) evaluator would be a nice addition to Cadmium IMO.
I can work on a PR if you're ok with it.
More evaluators can be implemented so I'm pla…
-
Dear author,
Thank you for your amazing work appearing in COLING 18.
I found you reported the WES in your paper. However, I couldn't find any corresponding metric computing script in your reposito…
-
Hi everyone,
I was wondering if you were planning to implement Word Error Rate (WER). Even though WER is mostly used to test speech systems, It wouldn't be a bad idea to have a reproducible WER on …
-
Hi WhisperX Team,
I was wondering if you consider support https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/whisper the tensorrt-llm backend of whisper. I have done several benchmark test us…
-
Next up on the todo list, given two transcripts (a ground truth and a generated), calculate the following:
* Overall similarity (done in #3)
* Word-Error-Rate (this looks promising: https://github…
-
Hi!
Is there a guide to implement MWER Training in lingvo? I have tried to write the code from scratch, but it is a really difficult to me. I'm trying the beam-srarch based N-best MWER Training as a …
-
Hello,
I installed Julius 4.3.1 on windows/Cygwin and used my own Arabic acoustic model HTK 3.4, corpus 8.5 hours, ngram LM, tied.list. The decoder is working well. However, the results is far away f…