-
I want to implement RNN-T for asr.
I am finding it difficult to start implementation.
Is it even a good idea to use Lingvo to implement RNN-T for streaming ASR?
Some guidance will be helpful.
Th…
-
Hi everyone,
I tried to run the ASR task with both the Librispeech960Base model and the Librispeech960Grapheme one. I don't know exactly the output that I should get to be sure that everything ended …
-
Hi,
I'm trying to download preprocess the dataset for the ASR task with the files: _lingvo/tasks/asr/tools/librispeech.03.parameterize_train.sh_ and _lingvo/tasks/asr/tools/librispeech.04.parameteriz…
-
官网示例中都是中文语音识别
```
>>> from paddlespeech.cli.asr.infer import ASRExecutor
>>> asr = ASRExecutor()
>>> result = asr(audio_file="zh.wav")
>>> print(result)
我认为跑步最重要的就是给我带来了身体健康
```
当然用这份代码跑中文也会报错…
-
Hello,
I successfully installed the environment according to the README, but when I run search_genetic.py using the default command given, I cannot get the expected ASR. I'm confused that the models …
-
Hi, I want to use Whisper lora finetune for my asr task.
So I add asr_config=conf/tuning/train_asr_whisper_medium_lora_finetune.yaml, inference_config=conf/tuning/decode_asr_whisper_noctc_beam10.yam…
ily6 updated
5 months ago
-
Hello! Thanks for your wonderful work. Trying to reproduce your results on the TTS task, I'm wondering if you could provide more details about the evaluation of the TTS task, especially:
- How many…
Btlmd updated
1 month ago
-
The current implementation of count expects value of `dim` at compile time.
```fortran
program main
logical :: mask(3, 4)
integer :: dim
mask = .true.
dim = 2
print *, count(mask, dim)
end…
-
Requested in #3046.
```fortran
submodule (stdlib_math) stdlib_math_all_close
end submodule stdlib_math_all_close
```
> LFortran
```console
% lfortran a.f90 --show-llvm
Internal Compile…
-
Here is how to improve our ASR types design and simplify backends and improve optimizations. Here is "ab-initio" derivation:
* ASR has to have types. Why? To ensure (using verify()) that all the pi…