-
When I'm run
python examples/mms/asr/infer/mms_infer.py --model "/path/to/asr/model" --lang lang_code --audio "/path/to/audio_1.wav" "/path/to/audio_1.wav"
I got this error:
>>> preparing tmp man…
-
**Describe the bug**
比如：` 这样的训练过程使得我能够回答各种问题、创作文字，以及进行多轮对话等任务。` 这段文字，使用 CosyVoice-300M-SFT 模型推理生成的语音， `、` 之后的文字没有生成语音。
**To Reproduce**
```
from cosyvoice.cli.cosyvoice import CosyVoice
from c…
-
@czgdp1807 wrote in: https://github.com/lcompilers/lpython/pull/816#issuecomment-1193346374
> Supporting this in backends would be an interesting problem. Reason being neither LLVM nor C/C++ suppor…
-
1. 增加训练代码；
2. 微调现有模型；
3. 模型大小可配置；
-
Hi,
I download the fairseq [checkpoint](https://drive.google.com/file/d/1XJJ6A3xEMLjRbaO4z9FI-RP84fA4pvep/view) from readme.
The `inference/beam_search.py` is for asr I think, so I trying to runn…
-
# Task Name
Audio Searching
## Task Objective
In this task, we aim to use ASR with timestamping to implement searching for words or sentences in an audio file. This is a valuable task that enhanc…
-
采用docker paddle-> 2.5.1镜像安装编译 paddleSpeech 1.4.0 版本的，启动 demos/speech_web/speech_server/main.py 的时候，报如下错误，求助原因：
[2023-09-05 01:14:41,309] [ WARNING] - The sample rate of the input file is not 16000.…
-
repro: https://github.com/rebcabin/lpython/tree/brian-lasr/lasr/LP-pycharm/Issue1992
the offending code:
```python
def regex_test() -> None:
print('REGEX TEST')
assert ord('a') >= ord…
-
**Describe the bug**
Using the current state of main, ASR and NLP worker jobs are not getting triggered when importing new source (e.g. served devset feed), although sliders in Importer are set corre…
-
请问你们训练语料中有中文吗，对中文语音的支持如何？
谢谢！