-
### 🐛 Describe the bug
The `MaxTokenBucketizer` data pipe should probably be aware whether users will pad the resulting list of data to equal length. As the description gives an example in the audi…
-
Thanks for the clear example In folder`templates/speech_recognition/ASR/` to train an ASR model on mini-librispeech dataset. However, when I used the librispeech-pretrained model (ASR model, language …
-
### System Info
```shell
- `transformers` version: 4.21.0.dev0
- Platform: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic
- Python version: 3.7.13
- Huggingface_hub version: 0.8.1
- PyTorch ve…
-
I don't think that matters for the DNN at the end of the day but I've made some kind of avg mean on the numbers of librispeech and aspire recipes. This is just for logging / reporting purposes.
One…
-
The following gave me good results on the easy "clean" part of Librispeech. Might be helpful for others:-)
1. Download a fine-tuned wav2vec AM:
`$ wget https://dl.fbaipublicfiles.com/fairseq/wav…
-
# 【PaddlePaddle Hackathon 4】模型套件开源贡献任务合集
（此 ISSUE 为 PaddlePaddle Hackathon 第四期活动的任务 ISSUE，更多详见 [【PaddlePaddle Hackathon 第四期】任务总览](https://github.com/PaddlePaddle/Paddle/issues/50629)）
注：开发请参考 [贡…
-
Hi,
I trained a model using egs/librispeech/ASR/pruned_transducer_stateless2 and decoding works fine with all the default search strategies in pruned_transducer_stateless2/decode.py: greedy_search,…
-
I resume to train wenetspeech model by specifying --start-batch 24000, related code is listed below:
```
python3 ./pruned_transducer_stateless5/train.py \
--start-batch 24000 \
--use-fp16 True…
-
You would like to see a new example being implemented by the Flax core team or the community? Please let us know by filling the following template.
### Description of the model to be implemented
R…
-
### System Info
```shell
- `transformers` version: 4.18.0
- Platform: Linux-5.4.0-109-generic-x86_64-with-glibc2.27
- Python version: 3.8.8
- Huggingface_hub version: 0.5.1
- PyTorch version (GPU…