icefall
icefall copied to clipboard
k2-fsa
This pull request is for the SEAME recipe and includes the following: 1. Standard Zipformer with RNNT loss 2. Zipformer with hybrid autoregressive transducer (HAT) loss 3. Proposed Zipformer with...
Hello, thank you for making such a great toolkit. I am reproducing [pruned_transducer_stateless7](https://github.com/k2-fsa/icefall/tree/c45e9fecfb89bada0233a7b6cd9626fb6633a696/egs/ami/ASR/pruned_transducer_stateless7) on AMI corpus. When I applied GSS enhancer to training data (prepare.sh: stage 3, local/prepare_ami_gss.sh: stage 4),...
Please see https://livejohnshopkins-my.sharepoint.com/:p:/g/personal/mwiesne2_jh_edu/EYqRDl8cIr5BsVDxi1MOW5EBUpdqh10WFkzqixPIFM63hg?e=u3lrmL
Add a recipe for [MLS](https://arxiv.org/pdf/2012.03411). More descriptions will follow.
This PR supports CTC/AED system for `zipformer` recipe. * CTC/AED results on LibriSpeech, trained for 50 epochs (--ctc-loss-scale=0.1, --attention-decoder-loss-scale=0.9), decoding method: sample 100-best paths from CTC lattice and rescore with...
Hi all, This PR is to support the recipe for [ICMC-ASR competition](https://icmcasr.org/). Processing the IHM and SDM data, along with baseline AEC-IVA and GSS approach are included in this recipe....
Hi, I am trying to use SURT AMI recipe to adapt pre-trained model (SURT_BASE) to my data. I have prepared dataset similarly to AMI & ISCI datasets preparations, CutSet contains...
It is based on [CTC FORCED ALIGNMENT API TUTORIAL](https://pytorch.org/audio/main/tutorials/ctc_forced_alignment_api_tutorial.html) from [torchaudio](https://github.com/pytorch/audio), but we are using an FST-based approach. I can produce identical output with [torchaudio](https://github.com/pytorch/audio) using https://github.com/k2-fsa/kaldi-decoder. I am refactoring...
I have extensively used Zipformer model (both streaming and non-streaming variant) and I have noticed the following errors. The test has been done with greedy search and as well as...
