From 30aa982bf29ceefaf52c0013c12c19adc57dea0e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 27 四月 2023 21:11:04 +0800
Subject: [PATCH] docs
---
egs_modelscope/tp/TEMPLATE/README.md | 20 ++++++++++----------
1 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/egs_modelscope/tp/TEMPLATE/README.md b/egs_modelscope/tp/TEMPLATE/README.md
index f511f58..d33d4e6 100644
--- a/egs_modelscope/tp/TEMPLATE/README.md
+++ b/egs_modelscope/tp/TEMPLATE/README.md
@@ -1,4 +1,4 @@
-# TIMESTAMP PREDICTION
+# Timestamp Prediction (FA)
## Inference
@@ -8,12 +8,12 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
-inference_pipline = pipeline(
+inference_pipeline = pipeline(
task=Tasks.speech_timestamp,
model='damo/speech_timestamp_prediction-v1-16k-offline',
output_dir=None)
-rec_result = inference_pipline(
+rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_timestamps.wav',
text_in='涓� 涓� 涓� 澶� 骞� 娲� 鍥� 瀹� 涓� 浠� 涔� 璺� 鍒� 瑗� 澶� 骞� 娲� 鏉� 浜� 鍛�',)
print(rec_result)
@@ -23,15 +23,15 @@
-#### API-reference
-##### Define pipeline
+### API-reference
+#### Define pipeline
- `task`: `Tasks.speech_timestamp`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
- `ncpu`: `1` (Default), sets the number of threads used for intraop parallelism on CPU
- `output_dir`: `None` (Default), the output path of results if set
- `batch_size`: `1` (Default), batch size when decoding
-##### Infer pipeline
+#### Infer pipeline
- `audio_in`: the input speech to predict, which could be:
- wav_path, `e.g.`: asr_example.wav (wav in local or url),
- wav.scp, kaldi style wav list (`wav_id wav_path`), `e.g.`:
@@ -59,11 +59,11 @@
```
### Inference with multi-thread CPUs or multi GPUs
-FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/vad/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
+FunASR also offer recipes [egs_modelscope/tp/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/tp/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
- Setting parameters in `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- - `data_dir`: the dataset dir **must** include `wav.scp` and `text.scp`
+ - `data_dir`: the dataset dir **must** include `wav.scp` and `text.txt`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
@@ -78,7 +78,7 @@
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
--data_dir "./data/test" \
--output_dir "./results" \
- --batch_size 64 \
+ --batch_size 1 \
--gpu_inference true \
--gpuid_list "0,1"
```
@@ -89,7 +89,7 @@
--data_dir "./data/test" \
--output_dir "./results" \
--gpu_inference false \
- --njob 64
+ --njob 1
```
## Finetune with pipeline
--
Gitblit v1.9.1