-
in line 205-207, I think for attack like refool. The logic of the current implementation is for front n_poison samples, randomly find a non-target sample and make it become a poisoned sample by adding…
-
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…
-
## Task Name
Domain-specific code-switching speech recognition for Machine Learning Course.
## Task Objective
Transcribe code-switched speech in NTUML2021 course.
## Datasets
The videos are f…
-
*Original issue*: https://gitlab.com/lfortran/lfortran/-/issues/764
When `kind(0.d0)` is used, the `ASR` includes the (overloaded) `kind()` with `logical` parameter. As we are passing `0.d0` (which s…
-
我下载了最新的master代码，解压了数据，然后训练也可以跑起来：
[*Info] Create Model Successful, Compiles Model Successful.
[running] train epoch 0 .
[message] epoch 0 . Have train datas 0+
Epoch 1/1
500/500 [===============…
-
### Feature Use Case
Implement OpenAI Whisper ASR for SOTA TTS and wakeword triggers.
### Feature Proposal
OpenAI recently released Whisper, a SOTA ASR model. Recent development on Whisper in…
-
您好，我想在悟空中使用讯飞的语音识别服务，但在config文件中讯飞语音服务中不知如何配置下面两项：
asr_api_key: '' # 语音听写
tts_api_key: '' # 在线语音合
讯飞语音的控制台中只有APPID、APISecret、APIKey，其中APIKey或APISecret适用于WebAPI调用方式，我尝试过把APISecret配入asr_api_key，但是…
-
我按照安装教程，环境都配好了，执行这个asr服务报错
W1025 11:49:38.739352 41545 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.6, Runtime API Version: 11.6
W1025 11:49:38.7…
-
## Goal
Currently if you interupt ichigo it will just start a new turn (at best)
## Description
With emperical result from this paper you can turn the LLM into non-turn based, which mean if you i…
-
Hello,
I have installed espnet toolkit as mentioned in the documentation and created a new recipe to perform self-supervised learning representations task. But, I am not sure why I'm always getting t…