From 048543b1cd2f0150d8bc4cbfb2b6436ac8e09032 Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期四, 19 十月 2023 15:03:49 +0800 Subject: [PATCH] docs --- egs_modelscope/vad/TEMPLATE/README.md | 2 +- egs_modelscope/asr/TEMPLATE/README.md | 7 +++---- egs_modelscope/vad/TEMPLATE/README_zh.md | 2 +- 3 files changed, 5 insertions(+), 6 deletions(-) diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md index ae81e57..bf6d30b 100644 --- a/egs_modelscope/asr/TEMPLATE/README.md +++ b/egs_modelscope/asr/TEMPLATE/README.md @@ -45,10 +45,9 @@ - `max_single_segment_time`: The maximum length for audio segmentation in VAD, specified in `ms`. Suggestion: When encountering OOM (Out of Memory) issues with long audio inputs, as the GPU memory usage increases with the square of the audio duration, there are three possible scenarios: - -a) In the initial inference stage, GPU memory usage primarily depends on `batch_size_token`. Reducing this value appropriately can help reduce memory usage. -b) In the middle of the inference process, when encountering long audio segments segmented by VAD, if the total number of tokens is still smaller than `batch_size_token` but OOM issues persist, reducing `batch_size_token_threshold_s` can help. If the threshold is exceeded, forcing the batch size to 1 can be considered. -c) Towards the end of the inference process, when encountering long audio segments segmented by VAD and the total number of tokens is smaller than `batch_size_token` but exceeds the threshold `batch_size_token_threshold_s`, forcing the batch size to 1 may still result in OOM errors. In such cases, reducing `max_single_segment_time` can be considered to shorten the duration of audio segments generated by VAD. +- a) In the initial inference stage, GPU memory usage primarily depends on `batch_size_token`. Reducing this value appropriately can help reduce memory usage. +- b) In the middle of the inference process, when encountering long audio segments segmented by VAD, if the total number of tokens is still smaller than `batch_size_token` but OOM issues persist, reducing `batch_size_token_threshold_s` can help. If the threshold is exceeded, forcing the batch size to 1 can be considered. +- c) Towards the end of the inference process, when encountering long audio segments segmented by VAD and the total number of tokens is smaller than `batch_size_token` but exceeds the threshold `batch_size_token_threshold_s`, forcing the batch size to 1 may still result in OOM errors. In such cases, reducing `max_single_segment_time` can be considered to shorten the duration of audio segments generated by VAD. #### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) ##### Streaming Decoding diff --git a/egs_modelscope/vad/TEMPLATE/README.md b/egs_modelscope/vad/TEMPLATE/README.md index 35897ca..2651dce 100644 --- a/egs_modelscope/vad/TEMPLATE/README.md +++ b/egs_modelscope/vad/TEMPLATE/README.md @@ -36,7 +36,7 @@ speech_chunk = speech[0:chunk_stride] rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict) print(rec_result) -# next chunk, 480ms +# next chunk, 100ms speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride] rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict) print(rec_result) diff --git a/egs_modelscope/vad/TEMPLATE/README_zh.md b/egs_modelscope/vad/TEMPLATE/README_zh.md index 38123a4..8157e07 100644 --- a/egs_modelscope/vad/TEMPLATE/README_zh.md +++ b/egs_modelscope/vad/TEMPLATE/README_zh.md @@ -36,7 +36,7 @@ speech_chunk = speech[0:chunk_stride] rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict) print(rec_result) -# next chunk, 480ms +# next chunk, 100ms speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride] rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict) print(rec_result) -- Gitblit v1.9.1