python/FunASR-XL.git

parent: 20619400 | 补丁 | 提交 | ignore whitespace

游雁

2023-05-05 1fadb21eb61dc0e4df987eaf0f9c59bdacec6ca4

docs

7个文件已修改

	docs/modelscope_pipeline/quick_start.md	2 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/TEMPLATE/README.md	6 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/punctuation/TEMPLATE/README.md	6 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/speaker_diarization/TEMPLATE/README.md	4 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/speaker_verification/TEMPLATE/README.md	4 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/tp/TEMPLATE/README.md	4 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/vad/TEMPLATE/README.md	6 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史

 docs/modelscope_pipeline/quick_start.md

@@ -1,7 +1,7 @@
# Quick Start

> **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 typic model as example to demonstrate the usage.


## Inference with pipeline

 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 the typic models as examples 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

@@ -79,7 +79,7 @@
### 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
- `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
@@ -103,7 +103,7 @@
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.

#### Settings of `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
- `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

 egs_modelscope/punctuation/TEMPLATE/README.md

@@ -1,7 +1,7 @@
# Punctuation Restoration

> **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 finetune. Here we take the model of the punctuation model of CT-Transformer 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 finetune. Here we take the model of the punctuation model of CT-Transformer as example to demonstrate the usage.

## Inference

@@ -55,7 +55,7 @@
### API-reference
#### Define pipeline
- `task`: `Tasks.punctuation`
- `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
- `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
- `output_dir`: `None` (Default), the output path of results if set
- `model_revision`: `None` (Default), setting the model version
@@ -71,7 +71,7 @@
FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/punctuation/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs. It is an offline recipe and only support offline model.

#### Settings of `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
- `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 `punc.txt`
- `output_dir`: output dir of the recognition results
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference

 egs_modelscope/speaker_diarization/TEMPLATE/README.md

@@ -2,7 +2,7 @@

> **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) 
[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 model of xvector_sv as example to demonstrate the usage.

## Inference with pipeline
@@ -40,7 +40,7 @@
### API-reference
#### Define pipeline
- `task`: `Tasks.speaker_diarization`
- `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
- `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
- `output_dir`: `None` (Default), the output path of results if set
- `batch_size`: `1` (Default), batch size when decoding

 egs_modelscope/speaker_verification/TEMPLATE/README.md

@@ -2,7 +2,7 @@

> **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) 
[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 model of xvector_sv as example to demonstrate the usage.

## Inference with pipeline
@@ -50,7 +50,7 @@
### API-reference
#### Define pipeline
- `task`: `Tasks.speaker_verification`
- `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
- `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
- `output_dir`: `None` (Default), the output path of results if set
- `batch_size`: `1` (Default), batch size when decoding

 egs_modelscope/tp/TEMPLATE/README.md

@@ -26,7 +26,7 @@
### 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
- `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
@@ -62,7 +62,7 @@
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.

#### Settings of `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
- `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 **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

 egs_modelscope/vad/TEMPLATE/README.md

@@ -1,7 +1,7 @@
# Voice Activity Detection

> **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 finetune. Here we take the model of FSMN-VAD 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 finetune. Here we take the model of FSMN-VAD as example to demonstrate the usage.

## Inference

@@ -46,7 +46,7 @@
### API-reference
#### Define pipeline
- `task`: `Tasks.voice_activity_detection`
- `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
- `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
@@ -70,7 +70,7 @@
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.

#### Settings of `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
- `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`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu

			@@ -1,7 +1,7 @@
			# Quick Start

			> 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 typic model as example to demonstrate the usage.


			## Inference with pipeline

			@@ -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 the typic models as examples 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

			@@ -79,7 +79,7 @@
			### 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
			- `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
			@@ -103,7 +103,7 @@
			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.

			#### Settings of `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
			- `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

			@@ -1,7 +1,7 @@
			# Punctuation Restoration

			> 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 finetune. Here we take the model of the punctuation model of CT-Transformer 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 finetune. Here we take the model of the punctuation model of CT-Transformer as example to demonstrate the usage.

			## Inference

			@@ -55,7 +55,7 @@
			### API-reference
			#### Define pipeline
			- `task`: `Tasks.punctuation`
			- `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
			- `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
			- `output_dir`: `None` (Default), the output path of results if set
			- `model_revision`: `None` (Default), setting the model version
			@@ -71,7 +71,7 @@
			FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/punctuation/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs. It is an offline recipe and only support offline model.

			#### Settings of `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
			- `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 `punc.txt`
			- `output_dir`: output dir of the recognition results
			- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference

			@@ -2,7 +2,7 @@

			> 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)
			[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 model of xvector_sv as example to demonstrate the usage.

			## Inference with pipeline
			@@ -40,7 +40,7 @@
			### API-reference
			#### Define pipeline
			- `task`: `Tasks.speaker_diarization`
			- `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
			- `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
			- `output_dir`: `None` (Default), the output path of results if set
			- `batch_size`: `1` (Default), batch size when decoding

			@@ -26,7 +26,7 @@
			### 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
			- `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
			@@ -62,7 +62,7 @@
			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.

			#### Settings of `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
			- `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 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

			@@ -1,7 +1,7 @@
			# Voice Activity Detection

			> 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 finetune. Here we take the model of FSMN-VAD 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 finetune. Here we take the model of FSMN-VAD as example to demonstrate the usage.

			## Inference

			@@ -46,7 +46,7 @@
			### API-reference
			#### Define pipeline
			- `task`: `Tasks.voice_activity_detection`
			- `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
			- `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
			@@ -70,7 +70,7 @@
			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.

			#### Settings of `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
			- `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`
			- `output_dir`: output dir of the recognition results
			- `batch_size`: `64` (Default), batch size of inference on gpu