From f97e0eb9eee3f14c410ce905b73d0c83033dc1c9 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 28 四月 2023 15:17:38 +0800
Subject: [PATCH] update
---
funasr/models/e2e_tp.py | 2
funasr/tasks/diar.py | 2
docs_cn/build_task.md | 2
docs/build_task.md | 2
funasr/main_funcs/calculate_all_attentions.py | 4 +-
funasr/main_funcs/collect_stats.py | 4 +-
egs/aishell/conformer/run.sh | 57 ++++++++++++++++++++++++++++
7 files changed, 64 insertions(+), 9 deletions(-)
diff --git a/docs/build_task.md b/docs/build_task.md
index be2d1af..2020860 100644
--- a/docs/build_task.md
+++ b/docs/build_task.md
@@ -103,7 +103,7 @@
)
return model
```
-This function defines the detail of the model. For different speech recognition models, the same speech recognition `Task` can usually be shared and the remaining thing needed to be done is to define a specific model in this function. For example, a speech recognition model with a standard encoder-decoder structure has been shown above. Specifically, it first defines each module of the model, including encoder, decoder, etc. and then combine these modules together to generate a complete model. In FunASR, the model needs to inherit `AbsESPnetModel` and the corresponding code can be seen in `funasr/train/abs_espnet_model.py`. The main function needed to be implemented is the `forward` function.
+This function defines the detail of the model. For different speech recognition models, the same speech recognition `Task` can usually be shared and the remaining thing needed to be done is to define a specific model in this function. For example, a speech recognition model with a standard encoder-decoder structure has been shown above. Specifically, it first defines each module of the model, including encoder, decoder, etc. and then combine these modules together to generate a complete model. In FunASR, the model needs to inherit `FunASRModel` and the corresponding code can be seen in `funasr/train/abs_espnet_model.py`. The main function needed to be implemented is the `forward` function.
Next, we take `SANMEncoder` as an example to introduce how to use a custom encoder as a part of the model when defining the specified model and the corresponding code can be seen in `funasr/models/encoder/sanm_encoder.py`. For a custom encoder, in addition to inheriting the common encoder class `AbsEncoder`, it is also necessary to define the `forward` function to achieve the forward computation of the `encoder`. After defining the `encoder`, it should also be registered in the `Task`. The corresponding code example can be seen as below:
```python
diff --git a/docs_cn/build_task.md b/docs_cn/build_task.md
index c23b19f..61f00ff 100644
--- a/docs_cn/build_task.md
+++ b/docs_cn/build_task.md
@@ -102,7 +102,7 @@
)
return model
```
-璇ュ嚱鏁板畾涔変簡鍏蜂綋鐨勬ā鍨嬨�傚浜庝笉鍚岀殑璇煶璇嗗埆妯″瀷锛屽線寰�鍙互鍏辩敤鍚屼竴涓闊宠瘑鍒玚Task`锛岄澶栭渶瑕佸仛鐨勬槸鍦ㄦ鍑芥暟涓畾涔夌壒瀹氱殑妯″瀷銆備緥濡傦紝杩欓噷缁欏嚭鐨勬槸涓�涓爣鍑嗙殑encoder-decoder缁撴瀯鐨勮闊宠瘑鍒ā鍨嬨�傚叿浣撳湴锛屽厛瀹氫箟璇ユā鍨嬬殑鍚勪釜妯″潡锛屽寘鎷琫ncoder锛宒ecoder绛夛紝鐒跺悗鍦ㄥ皢杩欎簺妯″潡缁勫悎鍦ㄤ竴璧峰緱鍒颁竴涓畬鏁寸殑妯″瀷銆傚湪FunASR涓紝妯″瀷闇�瑕佺户鎵縛AbsESPnetModel`锛屽叾鍏蜂綋浠ｇ爜瑙乣funasr/train/abs_espnet_model.py`锛屼富瑕侀渶瑕佸疄鐜扮殑鏄痐forward`鍑芥暟銆�
+璇ュ嚱鏁板畾涔変簡鍏蜂綋鐨勬ā鍨嬨�傚浜庝笉鍚岀殑璇煶璇嗗埆妯″瀷锛屽線寰�鍙互鍏辩敤鍚屼竴涓闊宠瘑鍒玚Task`锛岄澶栭渶瑕佸仛鐨勬槸鍦ㄦ鍑芥暟涓畾涔夌壒瀹氱殑妯″瀷銆備緥濡傦紝杩欓噷缁欏嚭鐨勬槸涓�涓爣鍑嗙殑encoder-decoder缁撴瀯鐨勮闊宠瘑鍒ā鍨嬨�傚叿浣撳湴锛屽厛瀹氫箟璇ユā鍨嬬殑鍚勪釜妯″潡锛屽寘鎷琫ncoder锛宒ecoder绛夛紝鐒跺悗鍦ㄥ皢杩欎簺妯″潡缁勫悎鍦ㄤ竴璧峰緱鍒颁竴涓畬鏁寸殑妯″瀷銆傚湪FunASR涓紝妯″瀷闇�瑕佺户鎵縛FunASRModel`锛屽叾鍏蜂綋浠ｇ爜瑙乣funasr/train/abs_espnet_model.py`锛屼富瑕侀渶瑕佸疄鐜扮殑鏄痐forward`鍑芥暟銆�
涓嬮潰鎴戜滑灏嗕互`SANMEncoder`涓轰緥锛屼粙缁嶅浣曞湪瀹氫箟妯″瀷鐨勬椂鍊欙紝浣跨敤鑷畾涔夌殑`encoder`鏉ヤ綔涓烘ā鍨嬬殑缁勬垚閮ㄥ垎锛屽叾鍏蜂綋鐨勪唬鐮佽`funasr/models/encoder/sanm_encoder.py`銆傚浜庤嚜瀹氫箟鐨刞encoder`锛岄櫎浜嗛渶瑕佺户鎵块�氱敤鐨刞encoder`绫籤AbsEncoder`澶栵紝杩橀渶瑕佽嚜瀹氫箟`forward`鍑芥暟锛屽疄鐜癭encoder`鐨勫墠鍚戣绠椼�傚湪瀹氫箟瀹宍encoder`鍚庯紝杩橀渶瑕佸湪`Task`涓鍏惰繘琛屾敞鍐岋紝涓嬮潰缁欏嚭浜嗙浉搴旂殑浠ｇ爜绀轰緥锛�
```python
diff --git a/egs/aishell/conformer/run.sh b/egs/aishell/conformer/run.sh
index 05d35b7..979834b 100755
--- a/egs/aishell/conformer/run.sh
+++ b/egs/aishell/conformer/run.sh
@@ -16,7 +16,6 @@
feats_dir="../DATA" #feature output dictionary
exp_dir="."
lang=zh
-dumpdir=dump/fbank
feats_type=fbank
token_type=char
scp=wav.scp
@@ -143,4 +142,60 @@
} &
done
wait
+fi
+
+# Testing Stage
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: Inference"
+ for dset in ${test_sets}; do
+ asr_exp=${exp_dir}/exp/${model_dir}
+ inference_tag="$(basename "${inference_config}" .yaml)"
+ _dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
+ _logdir="${_dir}/logdir"
+ if [ -d ${_dir} ]; then
+ echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
+ exit 0
+ fi
+ mkdir -p "${_logdir}"
+ _data="${feats_dir}/data/${dset}"
+ key_file=${_data}/${scp}
+ num_scp_file="$(<${key_file} wc -l)"
+ _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
+ split_scps=
+ for n in $(seq "${_nj}"); do
+ split_scps+=" ${_logdir}/keys.${n}.scp"
+ done
+ # shellcheck disable=SC2086
+ utils/split_scp.pl "${key_file}" ${split_scps}
+ _opts=
+ if [ -n "${inference_config}" ]; then
+ _opts+="--config ${inference_config} "
+ fi
+ ${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
+ python -m funasr.bin.asr_inference_launch \
+ --batch_size 1 \
+ --ngpu "${_ngpu}" \
+ --njob ${njob} \
+ --gpuid_list ${gpuid_list} \
+ --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
+ --key_file "${_logdir}"/keys.JOB.scp \
+ --asr_train_config "${asr_exp}"/config.yaml \
+ --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
+ --output_dir "${_logdir}"/output.JOB \
+ --mode asr \
+ ${_opts}
+
+ for f in token token_int score text; do
+ if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
+ for i in $(seq "${_nj}"); do
+ cat "${_logdir}/output.${i}/1best_recog/${f}"
+ done | sort -k1 >"${_dir}/${f}"
+ fi
+ done
+ python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+ python utils/proce_text.py ${_data}/text ${_data}/text.proc
+ python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
+ tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
+ cat ${_dir}/text.cer.txt
+ done
fi
\ No newline at end of file
diff --git a/funasr/main_funcs/calculate_all_attentions.py b/funasr/main_funcs/calculate_all_attentions.py
index 8f238c6..c3bf015 100644
--- a/funasr/main_funcs/calculate_all_attentions.py
+++ b/funasr/main_funcs/calculate_all_attentions.py
@@ -21,12 +21,12 @@
from funasr.modules.attention import MultiHeadedAttention
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
@torch.no_grad()
def calculate_all_attentions(
- model: AbsESPnetModel, batch: Dict[str, torch.Tensor]
+ model: FunASRModel, batch: Dict[str, torch.Tensor]
) -> Dict[str, List[torch.Tensor]]:
"""Derive the outputs from the all attention layers
diff --git a/funasr/main_funcs/collect_stats.py b/funasr/main_funcs/collect_stats.py
index bacda8f..584b85a 100644
--- a/funasr/main_funcs/collect_stats.py
+++ b/funasr/main_funcs/collect_stats.py
@@ -17,12 +17,12 @@
from funasr.fileio.npy_scp import NpyScpWriter
from funasr.torch_utils.device_funcs import to_device
from funasr.torch_utils.forward_adaptor import ForwardAdaptor
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
@torch.no_grad()
def collect_stats(
- model: AbsESPnetModel,
+ model: FunASRModel,
train_iter: DataLoader and Iterable[Tuple[List[str], Dict[str, torch.Tensor]]],
valid_iter: DataLoader and Iterable[Tuple[List[str], Dict[str, torch.Tensor]]],
output_dir: Path,
diff --git a/funasr/models/e2e_tp.py b/funasr/models/e2e_tp.py
index 39419c8..33948f9 100644
--- a/funasr/models/e2e_tp.py
+++ b/funasr/models/e2e_tp.py
@@ -29,7 +29,7 @@
yield
-class TimestampPredictor(AbsESPnetModel):
+class TimestampPredictor(FunASRModel):
"""
Author: Speech Lab of DAMO Academy, Alibaba Group
"""
diff --git a/funasr/tasks/diar.py b/funasr/tasks/diar.py
index 0fa8c83..6be75a0 100644
--- a/funasr/tasks/diar.py
+++ b/funasr/tasks/diar.py
@@ -106,7 +106,7 @@
sond=DiarSondModel,
eend_ola=DiarEENDOLAModel,
),
- type_check=AbsESPnetModel,
+ type_check=FunASRModel,
default="sond",
)
encoder_choices = ClassChoices(
--
Gitblit v1.9.1