From a513d1ac95ae6f7d7cbc6dfefc9bbb3f78718163 Mon Sep 17 00:00:00 2001
From: Lizerui9926 <110582652+Lizerui9926@users.noreply.github.com>
Date: 星期二, 04 四月 2023 14:35:36 +0800
Subject: [PATCH] Merge pull request #325 from alibaba-damo-academy/dev_lzr
---
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh | 4 ++--
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py | 2 +-
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh | 4 ++--
funasr/bin/asr_inference_paraformer_vad.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py | 2 +-
funasr/bin/asr_inference_rnnt.py | 4 ++--
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py | 2 +-
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py | 2 +-
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py | 2 +-
egs/aishell/transformer/utils/compute_wer.py | 4 ++--
funasr/bin/asr_inference_paraformer.py | 2 +-
funasr/bin/asr_inference_uniasr.py | 4 ++--
funasr/bin/asr_inference_uniasr_vad.py | 4 ++--
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py | 2 +-
funasr/utils/compute_wer.py | 4 ++--
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py | 2 +-
funasr/bin/asr_inference_paraformer_vad_punc.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py | 2 +-
20 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/egs/aishell/transformer/utils/compute_wer.py b/egs/aishell/transformer/utils/compute_wer.py
index 349a3f6..26a9f49 100755
--- a/egs/aishell/transformer/utils/compute_wer.py
+++ b/egs/aishell/transformer/utils/compute_wer.py
@@ -45,8 +45,8 @@
if out_item['wrong'] > 0:
rst['wrong_sentences'] += 1
cer_detail_writer.write(hyp_key + print_cer_detail(out_item) + '\n')
- cer_detail_writer.write("ref:" + '\t' + "".join(ref_dict[hyp_key]) + '\n')
- cer_detail_writer.write("hyp:" + '\t' + "".join(hyp_dict[hyp_key]) + '\n')
+ cer_detail_writer.write("ref:" + '\t' + " ".join(list(map(lambda x: x.lower(), ref_dict[hyp_key]))) + '\n')
+ cer_detail_writer.write("hyp:" + '\t' + " ".join(list(map(lambda x: x.lower(), hyp_dict[hyp_key]))) + '\n')
if rst['Wrd'] > 0:
rst['Err'] = round(rst['wrong_words'] * 100 / rst['Wrd'], 2)
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py
index c016c19..77b2cbd 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py
@@ -74,7 +74,7 @@
# If text exists, compute CER
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(best_recog_path, "token")
+ text_proc_file = os.path.join(best_recog_path, "text")
compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
index b326067..488936c 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
@@ -38,7 +38,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py
index 54cfec0..0d06377 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py
@@ -74,7 +74,7 @@
# If text exists, compute CER
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(best_recog_path, "token")
+ text_proc_file = os.path.join(best_recog_path, "text")
compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
index 2f038a8..c94f685 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
@@ -38,7 +38,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
index f080257..221479d 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
@@ -63,8 +63,8 @@
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
echo "Computing WER ..."
- python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
- python utils/proce_text.py ${data_dir}/text ${output_dir}/1best_recog/text.ref
+ cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+ cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
tail -n 3 ${output_dir}/1best_recog/text.cer
fi
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
index 295c95d..2d311dd 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
@@ -34,7 +34,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
index cdf81dc..6daf7d4 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
@@ -63,8 +63,8 @@
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
echo "Computing WER ..."
- python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
- python utils/proce_text.py ${data_dir}/text ${output_dir}/1best_recog/text.ref
+ cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+ cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
tail -n 3 ${output_dir}/1best_recog/text.cer
fi
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
index e8fee02..747b49f 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
@@ -34,7 +34,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
index 5d74837..96db5f9 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
@@ -75,7 +75,7 @@
# If text exists, compute CER
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(best_recog_path, "token")
+ text_proc_file = os.path.join(best_recog_path, "text")
compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
index 861fefb..74691f0 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
@@ -39,7 +39,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
index 5c62362..8b4a04d 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
@@ -75,7 +75,7 @@
# If text exists, compute CER
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(best_recog_path, "token")
+ text_proc_file = os.path.join(best_recog_path, "text")
compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
index d73cae2..fd124ff 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
@@ -39,7 +39,7 @@
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+ text_proc_file = os.path.join(decoding_path, "1best_recog/text")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 2eeffcd..8cbd419 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -797,7 +797,7 @@
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
if writer is not None:
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
logging.info("decoding, utt: {}, predictions: {}".format(key, text))
rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))
diff --git a/funasr/bin/asr_inference_paraformer_vad.py b/funasr/bin/asr_inference_paraformer_vad.py
index a0dc0aa..1548f9f 100644
--- a/funasr/bin/asr_inference_paraformer_vad.py
+++ b/funasr/bin/asr_inference_paraformer_vad.py
@@ -338,7 +338,7 @@
ibest_writer["token"][key] = " ".join(token)
ibest_writer["token_int"][key] = " ".join(map(str, token_int))
ibest_writer["vad"][key] = "{}".format(vadsegments)
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
ibest_writer["text_with_punc"][key] = text_postprocessed_punc
if time_stamp_postprocessed is not None:
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index ab3e1e3..9dc0b79 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -670,7 +670,7 @@
ibest_writer["token"][key] = " ".join(token)
ibest_writer["token_int"][key] = " ".join(map(str, token_int))
ibest_writer["vad"][key] = "{}".format(vadsegments)
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
ibest_writer["text_with_punc"][key] = text_postprocessed_punc
if time_stamp_postprocessed is not None:
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
diff --git a/funasr/bin/asr_inference_rnnt.py b/funasr/bin/asr_inference_rnnt.py
index 4a9ff0b..2189a71 100644
--- a/funasr/bin/asr_inference_rnnt.py
+++ b/funasr/bin/asr_inference_rnnt.py
@@ -738,13 +738,13 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ text_postprocessed, word_lists = postprocess_utils.sentence_postprocess(token)
item = {'key': key, 'value': text_postprocessed}
asr_result_list.append(item)
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
if writer is not None:
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
logging.info("decoding, utt: {}, predictions: {}".format(key, text))
rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))
diff --git a/funasr/bin/asr_inference_uniasr.py b/funasr/bin/asr_inference_uniasr.py
index 7961d5a..2e5b6f5 100644
--- a/funasr/bin/asr_inference_uniasr.py
+++ b/funasr/bin/asr_inference_uniasr.py
@@ -507,13 +507,13 @@
ibest_writer["score"][key] = str(hyp.score)
if text is not None:
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ text_postprocessed, word_lists = postprocess_utils.sentence_postprocess(token)
item = {'key': key, 'value': text_postprocessed}
asr_result_list.append(item)
finish_count += 1
asr_utils.print_progress(finish_count / file_count)
if writer is not None:
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
return asr_result_list
return _forward
diff --git a/funasr/bin/asr_inference_uniasr_vad.py b/funasr/bin/asr_inference_uniasr_vad.py
index 3164d0d..52c29b8 100644
--- a/funasr/bin/asr_inference_uniasr_vad.py
+++ b/funasr/bin/asr_inference_uniasr_vad.py
@@ -507,13 +507,13 @@
ibest_writer["score"][key] = str(hyp.score)
if text is not None:
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ text_postprocessed, word_lists = postprocess_utils.sentence_postprocess(token)
item = {'key': key, 'value': text_postprocessed}
asr_result_list.append(item)
finish_count += 1
asr_utils.print_progress(finish_count / file_count)
if writer is not None:
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
return asr_result_list
return _forward
diff --git a/funasr/utils/compute_wer.py b/funasr/utils/compute_wer.py
index 349a3f6..26a9f49 100755
--- a/funasr/utils/compute_wer.py
+++ b/funasr/utils/compute_wer.py
@@ -45,8 +45,8 @@
if out_item['wrong'] > 0:
rst['wrong_sentences'] += 1
cer_detail_writer.write(hyp_key + print_cer_detail(out_item) + '\n')
- cer_detail_writer.write("ref:" + '\t' + "".join(ref_dict[hyp_key]) + '\n')
- cer_detail_writer.write("hyp:" + '\t' + "".join(hyp_dict[hyp_key]) + '\n')
+ cer_detail_writer.write("ref:" + '\t' + " ".join(list(map(lambda x: x.lower(), ref_dict[hyp_key]))) + '\n')
+ cer_detail_writer.write("hyp:" + '\t' + " ".join(list(map(lambda x: x.lower(), hyp_dict[hyp_key]))) + '\n')
if rst['Wrd'] > 0:
rst['Err'] = round(rst['wrong_words'] * 100 / rst['Wrd'], 2)
--
Gitblit v1.9.1