text

text copied to clipboard

Does the beam search decoder support RNN-T?

1

### Question I notice that CTC and ASG criterion are supported in the LexiconDecoderOptions, does it support RNN-T? how can I perform decoding for RNN-T models using flashlight? Thank you...

wp558

NameError: name 'CriterionType' is not defined

1

I am trying to decode a fine-tuned ASR model,fine-tuned using the [vakyansh](https://github.com/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation) toolkit using the [this](https://github.com/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation/blob/main/utils/inference/infer.py) script and the following command line:- python ../../utils/inference/infer.py ${data_path} --task audio_pretraining \ --nbest 1...

mukherjeesougata-eros

### Bug Description Hello, I'm trying to package this as a python package for NixOS, and I'm experiencing trouble due to the mixed cmake / `setup.py` layout. When I'm trying...

doronbehar

Static kTrieMaxLabel=6 causes issues with phoneme-based recognition

3

### Bug Description I tried building ASR systems on a very common standard task (LibriSpeech-100h) using the [torchaudio ctc decoder](https://pytorch.org/audio/stable/generated/torchaudio.models.decoder.ctc_decoder.html#torchaudio.models.decoder.ctc_decoder). This decoder uses the flashlight/text library as decoding backend. While...

JackTemaki

Migration from OpenSeq2Seq decoder to Flashlight

1

Hello, I am trying to migrate my ASR model from OpenSeq2Seq decoder to Flashlight. Currently, I am using [Nemo Conformer large](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_ctc_bpe.yaml) as the acoustic model, which is tuned on my...

Squire-tomsk

### Summary Adds diverse beam search from [this paper](https://arxiv.org/pdf/1610.02424.pdf). #### Helpful Diagrams Figure 1: Example of how diversity factor (Hamming) is applied at timestep *t* Figure 2: General algo ###...

joecummings

### Feature Description Currently, the dictionary cannot handle duplicate entries. It would be interesting if this would be supported. Possibly a flag that allows one to 'allow' multiples would be...

ThomasKluiters

### Feature Description Currently, the precompiled wheels are available for Python

foxik

I am using lexiconfreedecoder with kenlm arpa and bin language model. The decoder is loaded but the i am unable to decode using float emission values. I get the following...

sindhu-2507

Convert directory fbcode/deeplearning to use the Ruff Formatter

1

Summary: X-link: https://github.com/flashlight/flashlight/pull/1176 X-link: https://github.com/pytorch/FBGEMM/pull/3242 Converts the directory specified to use the Ruff formatter in pyfmt ruff_dog If this diff causes merge conflicts when rebasing, please run `hg status -n...

tpolasek