icefall
icefall copied to clipboard
k2-fsa
(sorry, I'm keeping track of this in an issue on github but this is not something accessible off our servers right now). Guys, As you know I've been working on...
I try to intersect output lattice (H) and LG and obtained the result using the 'intersect_device' function. But, sometimes it outputs empty hyp. ``` segment: 0 text: ``` Can you...
The ONNX exporting process currently exports five separate models: - ``encoder.onnx`` - ``decoder.onnx`` - ``joiner.onnx`` - ``joiner_encoder_proj.onnx`` - ``joiner_decoder_proj.onnx`` However, these models are just called sequentially, it doesn't look like...
Hello, I see that in LibriSpeech examples there are many different architectures. What architecture do you recommend to use for the case of 15,000 hours of data? Thanks, AlexG.
Hi, Is there a way to see when the model training will finish (something like a progress bar). I'm using `pruned_transducer_stateless5` recipe. Thanks.
No need to load_audio. alimeeting audio data is wav format, default export_to_webdataset uses "flac". If load_audio uses default (True), webdataset would show "[Suppressed TypeError] Error message: save() got an unexpected...
This PR adds: 1. Early and not tested implementation of https://wenet.org.cn/wenet/context.html
Hi, I see my output of decode has some case like this: ground truth transcript: "mở bài hát florentino" . The word: "florentino" is the word not in vietnamese (we...
In the last few days, a few people (>3) have encountered the following error after updating their lhotse to the latest version: ``` Segmentation fault (core dump) ``` when they...