johnchienbronci

Unsupported action found at bulk response.

1

Hi, elasticlient lib version: version-02 elastic-search version: 7.17.0 I'm bulk perform fail and without error. Checking log found a msg: Unsupported 'action' found at bulk response. deatail log: ``` Host...

test short audio file with silence between sentence, word timestamp may not be accurate

4

version: master (e9a082dcf27647eb52585cda6f115454c0ac6856) voice file: [test.mp3.zip](https://github.com/guillaumekln/faster-whisper/files/11170404/test.mp3.zip) voice file: Sentence and sentence duration of silence > 2s audio wav: set enable vad_filter and word_timestamp. Testing different scenarios, the word cannot be...

I encountered some errors when running the run_speech_recognition_ctc_streaming.sh by `deepspeed` ( `torchrun --nproc_per_node 1 ... `) and his issue consistently occurs with my custom corpora. Does anyone have any ideas?...

Hello, I have a testing project that involves the use of the TCP protocol. Reference: (https://github.com/processone/tsung/blob/develop/examples/raw.xml.in) However, I'm unsure about how to perform operations using the recv function. Are there...

kenlm 訓練自定義語言模型後似乎在糾錯及校正錯字上沒有效果

8

我目前測試是針對特定句子做訓練 text: .... 讓座 今天 應該 ... 訓練資訊 model = pycorrector.Corrector(language_model_path='corpus/lm.klm') correct_sent, detailect_sent = model.correct("少先隊員因該為老人讓坐") 結果沒有找出任何錯字 想請教是因為什麼原因導致校正錯字上沒效果

``` File "/usr/local/bin/source/huggingsound/examples/speech_recognition/finetune.py", line 71, in model.finetune( File "/usr/local/lib/python3.10/dist-packages/huggingsound/speech_recognition/model.py", line 353, in finetune train_dataset = self._get_dataset(processor, text_normalizer, train_data, train_data_cache_dir, training_args.length_column_name, num_workers) File "/usr/local/lib/python3.10/dist-packages/huggingsound/speech_recognition/model.py", line 272, in _get_dataset dataset = self._prepare_dataset_for_finetuning(dataset,...

How to use narrowband?

5

Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/lhotse/cut/mixed.py", line 285, in __getattr__) = self._assert_one_data_cut_with_attr_and_return_it_with_track_index(name) File "/usr/local/lib/python3.10/dist-packages/lhotse/cut/mixed.py", line 378, in _assert_one_data_cut_with_attr_and_return_it_with_track_index assert len(non_padding_cuts_with_custom_attr) == 1, ( AssertionError: This MixedCut has 0 non-padding...

trunction cause duration < 0

2

@pzelasko Hi As long as I add noise, and only read the segmentation audio file with (offset + duration) result: new_duration< 0 error ``` File "/usr/local/lib/python3.10/dist-packages/lhotse/dataset/sampling/dynamic_bucketing.py", line 299, in _next_batch...

[Bug] The number of declared samples in the recording diverged from the one obtained when loading audio (offset is 0.0)

14

@pzelasko sample rate: 16k The total length of the sound file: 48.92 s Read a segment of the audio file: offset: 0.0 duration: 4.948 and the following error will occur:...

Mismatch between x.size(1) and x_lens.max() due to subsampling length calculation

6

When training zipformer with CutConcatenate enabled, I hit an assertion error in subsampling.py in forward: ``` AssertionError: (1231, tensor(1232, device='cuda:5', dtype=torch.int32)) ``` The assertion is: assert x.size(1) == x_lens.max().item(), (x.size(1),...