-
```
即便是加上了这个参数，仍然爆显存。。。
```
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-…
-
**Describe your question**
Hi, im trying to use https://github.com/espnet/espnet/tree/master/egs2/covost2/st1 to train my own E2E AST model, and i want to reproduce your result on covost2 dataset.
U…
-
## 목적
- 오디오와 텍스트를 동시에 활용하는 Multimodal 모델은 오디오 입력과 텍스트 입력을 동시에 받아서 학습하는 경우가 많습니다. 사용자 입장에서 두가지를 동시에 입력하기란 불편하므로 결국 오디오 입력만 받고 이를 텍스트로 변환해야 할 것입니다.
## 상세내용
1. 음성을 텍스트로 변환하는 것은 공개된 무료 API를 활용합니다…
-
Hello， When I use bpe as the modeling unit to train the English ASR model, the output of model are bpe subwords, and words can be obtained by spaces and ‘__’. But this method doesn't seem to be able …
-
**Describe your question**
I just downloaded the modeI and trained it from scratch ,it seems there are no issues in the different stages from e2e but finally got result just like this :
![Upl…
-
```
File "/home/ybZhang/miniconda3/lib/python3.8/site-packages/funasr_onnx/vad_bin.py", line 116, in __call__
segments_part = self.vad_scorer(scores, waveform_package, is_final=is_final, max_end…
-
### System Info
DGX V100 and DGX A100
### Who can help?
@ncomly-nvidia to add more folks.
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An of…
-
I trained model using recipe/KosponSpeech, and got the transcribed text as below.
I used speechbrain version 0.5.12.
.....
KsponSpeech_E00099, %WER 0.00 [ 0 / 4, 0 ins, 0 del, 0 sub ]
반말을 ; 할 ; 수가…
-
Hi @csukuangfj , We are trying to benchmark offline icefall native decoding with ".pt" model vs sherpa offline websocket server decoding with torchscript model. We see that there is inconsistency in d…
-
Thank you for ESPnet team's continuous support. I have been using ESPnet and ESPnet2 for silent speech recogntion tasks for two years. (https://github.com/espnet/espnet/issues/1926)
I did visual sp…