From 47343b5c2f4e1256f60f46d8da0aa2e5de39b6c7 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期六, 05 八月 2023 17:53:08 +0800
Subject: [PATCH] init repo

---
 egs_modelscope/asr/TEMPLATE/README.md |  123 +++++++++++++++++++++++++++++-----------
 1 files changed, 89 insertions(+), 34 deletions(-)

diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index 3daff1f..0219c5b 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -1,7 +1,7 @@
 # Speech Recognition
 
 > **Note**: 
-> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take typic model as example to demonstrate the usage.
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take the typic models as examples to demonstrate the usage.
 
 ## Inference
 
@@ -19,30 +19,52 @@
 rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
 print(rec_result)
 ```
-#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+##### Streaming Decoding
 ```python
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
-    model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model_revision='v1.0.6',
+    update_model=False,
+    mode='paraformer_streaming'
     )
 import soundfile
 speech, sample_rate = soundfile.read("example/asr_example.wav")
 
-param_dict = {"cache": dict(), "is_final": False}
-chunk_stride = 7680# 480ms
-# first chunk, 480ms
+chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
+# first chunk, 600ms
 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, 600ms
 speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
 rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+```
+
+##### Fake Streaming Decoding
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model_revision='v1.0.6',
+    update_model=False,
+    mode="paraformer_fake_streaming"
+)
+audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
+rec_result = inference_pipeline(audio_in=audio_in)
 print(rec_result)
 ```
 Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
 
 #### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
-There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model detailes, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
 ```python
 decoding_model = "fast" # "fast"銆�"normal"銆�"offline"
 inference_pipeline = pipeline(
@@ -58,44 +80,62 @@
 #### [RNN-T-online model]()
 Undo
 
-#### API-reference
-##### Define pipeline
+#### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+For more model details, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
+    model_revision='v3.0.0'
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+
+### API-reference
+#### Define pipeline
 - `task`: `Tasks.auto_speech_recognition`
-- `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` (Defalut), decoding on GPU. If ngpu=0, decoding on CPU
-- `ncpu`: `1` (Defalut), sets the number of threads used for intraop parallelism on CPU 
-- `output_dir`: `None` (Defalut), the output path of results if set
-- `batch_size`: `1` (Defalut), batch size when decoding
-##### Infer pipeline
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/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
 - `audio_in`: the input to decode, which could be: 
   - wav_path, `e.g.`: asr_example.wav,
   - pcm_path, `e.g.`: asr_example.pcm, 
   - audio bytes stream, `e.g.`: bytes data from a microphone
   - audio sample point锛宍e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
-  - wav.scp, kaldi style wav list (`wav_id \t wav_path``), `e.g.`: 
+  - wav.scp, kaldi style wav list (`wav_id \t wav_path`), `e.g.`: 
   ```text
   asr_example1  ./audios/asr_example1.wav
   asr_example2  ./audios/asr_example2.wav
   ```
   In this case of `wav.scp` input, `output_dir` must be set to save the output results
 - `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
-- `output_dir`: None (Defalut), the output path of results if set
+- `output_dir`: None (Default), the output path of results if set
 
 ### Inference with multi-thread CPUs or multi GPUs
-FunASR also offer recipes [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
+FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/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 needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
-    - `output_dir`: output dir of the recognition results
-    - `batch_size`: `64` (Default), batch size of inference on gpu
-    - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
-    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
-    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
-    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
-    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+#### Settings of `infer.sh`
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
+- `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
+- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+- `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast銆乶ormal銆乷ffline)
+- `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
 
-- Decode with multi GPUs:
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -105,7 +145,7 @@
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -115,7 +155,7 @@
     --njob 64
 ```
 
-- Results
+#### Results
 
 The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
 
@@ -176,6 +216,21 @@
     - `max_epoch`: number of training epoch
     - `lr`: learning rate
 
+- Training data formats锛�
+```sh
+cat ./example_data/text
+BAC009S0002W0122 鑰� 瀵� 妤� 甯� 鎴� 浜� 鎶� 鍒� 浣� 鐢� 鏈� 澶� 鐨� 闄� 璐�
+BAC009S0002W0123 涔� 鎴� 涓� 鍦� 鏂� 鏀� 搴� 鐨� 鐪� 涓� 閽�
+english_example_1 hello world
+english_example_2 go swim 鍘� 娓� 娉�
+
+cat ./example_data/wav.scp
+BAC009S0002W0122 /mnt/data/wav/train/S0002/BAC009S0002W0122.wav
+BAC009S0002W0123 /mnt/data/wav/train/S0002/BAC009S0002W0123.wav
+english_example_1 /mnt/data/wav/train/S0002/english_example_1.wav
+english_example_2 /mnt/data/wav/train/S0002/english_example_2.wav
+```
+
 - Then you can run the pipeline to finetune with:
 ```shell
 python finetune.py
@@ -186,7 +241,7 @@
 ```
 ## Inference with your finetuned model
 
-- Setting parameters in [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) is the same with [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/egs_modelscope/asr/TEMPLATE#inference-with-multi-thread-cpus-or-multi-gpus) 
+- Setting parameters in [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) is the same with [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/egs_modelscope/asr/TEMPLATE#inference-with-multi-thread-cpus-or-multi-gpus), `model` is the model name from modelscope, which you finetuned.
 
 - Decode with multi GPUs:
 ```shell
@@ -210,4 +265,4 @@
     --njob 64 \
     --checkpoint_dir "./checkpoint" \
     --checkpoint_name "valid.cer_ctc.ave.pb"
-```
\ No newline at end of file
+```

--
Gitblit v1.9.1