Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
bugfix
游雁4cf44a89f808
diff --git a/examples/aishell/branchformer/run.sh b/examples/aishell/branchformer/run.shindex f4842d08c..dba8b96e2 100755--- a/examples/aishell/branchformer/run.sh+++ b/examples/aishell/branchformer/run.sh@@ -109,6 +109,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; thenlog_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"echo "log_file: ${log_file}"+ export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICESgpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')torchrun \--nnodes 1 \diff --git a/examples/aishell/conformer/run.sh b/examples/aishell/conformer/run.shindex ff99f9e2d..3029cbd07 100755--- a/examples/aishell/conformer/run.sh+++ b/examples/aishell/conformer/run.sh@@ -5,7 +5,7 @@ CUDA_VISIBLE_DEVICES="0,1"# general configurationfeats_dir="../DATA" #feature output dictionary-exp_dir="."+exp_dir=`pwd`lang=zhtoken_type=charstage=0@@ -109,6 +109,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; thenlog_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"echo "log_file: ${log_file}"+ export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICESgpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')torchrun \--nnodes 1 \@@ -129,7 +130,7 @@ fiif [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; thenecho "stage 5: Inference"- if ${inference_device} == "cuda"; then+ if [ ${inference_device} == "cuda" ]; thennj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')elseinference_batch_size=1@@ -170,7 +171,7 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then++input="${_logdir}/keys.${JOB}.scp" \++output_dir="${inference_dir}/${JOB}" \++device="${inference_device}" \- ++batch_size="${inference_batch_size}"+ ++batch_size="${inference_batch_size}" &> ${_logdir}/log.${JOB}.txt}&donediff --git a/examples/aishell/e_branchformer/run.sh b/examples/aishell/e_branchformer/run.shindex 0855798c7..ed765b872 100755--- a/examples/aishell/e_branchformer/run.sh+++ b/examples/aishell/e_branchformer/run.sh@@ -109,6 +109,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; thenlog_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"echo "log_file: ${log_file}"+ export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICESgpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')torchrun \--nnodes 1 \diff --git a/examples/aishell/paraformer/run.sh b/examples/aishell/paraformer/run.shindex 80f81b5f8..d6f1a2cbc 100755--- a/examples/aishell/paraformer/run.sh+++ b/examples/aishell/paraformer/run.sh@@ -109,6 +109,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; thenlog_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"echo "log_file: ${log_file}"+ export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICESgpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')torchrun \--nnodes 1 \diff --git a/examples/aishell/transformer/run.sh b/examples/aishell/transformer/run.shindex da6d4d6ab..3a0216168 100755--- a/examples/aishell/transformer/run.sh+++ b/examples/aishell/transformer/run.sh@@ -109,6 +109,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; thenlog_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"echo "log_file: ${log_file}"+ export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICESgpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')torchrun \--nnodes 1 \@@ -129,7 +130,7 @@ fiif [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; thenecho "stage 5: Inference"- if ${inference_device} == "cuda"; then+ if [ ${inference_device} == "cuda" ]; thennj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')elseinference_batch_size=1@@ -141,7 +142,7 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; thenfor dset in ${test_sets}; do- inference_dir="${exp_dir}/exp/${model_dir}/${inference_checkpoint}/${dset}"+ inference_dir="${exp_dir}/exp/${model_dir}/infer-${inference_checkpoint}/${dset}"_logdir="${inference_dir}/logdir"mkdir -p "${_logdir}"@@ -154,7 +155,7 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; thendoneutils/split_scp.pl "${key_file}" ${split_scps}- gpuid_list_array=(${gpuid_list//,/ })+ gpuid_list_array=(${CUDA_VISIBLE_DEVICES//,/ })for JOB in $(seq ${nj}); do{id=$((JOB-1))diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.py b/examples/industrial_data_pretraining/bicif_paraformer/demo.pyindex 90102006f..bb63872d2 100644--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.py+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.py@@ -11,8 +11,8 @@ model = AutoModel(model="damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16kvad_model_revision="v2.0.4",punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",punc_model_revision="v2.0.4",- spk_model="damo/speech_campplus_sv_zh-cn_16k-common",- spk_model_revision="v2.0.4",+ # spk_model="damo/speech_campplus_sv_zh-cn_16k-common",+ # spk_model_revision="v2.0.2",)res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_vad_punc_example.wav", batch_size_s=300, batch_size_threshold_s=60)diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.pyindex e95cfd8d1..e4a154dbb 100644--- a/funasr/auto/auto_model.py+++ b/funasr/auto/auto_model.py@@ -400,20 +400,20 @@ class AutoModel:for res, vadsegment in zip(restored_data, vadsegments):sentence_list.append({"start": vadsegment[0],\"end": vadsegment[1],- "sentence": res['raw_text'],+ "sentence": res['text'],"timestamp": res['timestamp']})elif self.spk_mode == 'punc_segment':sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \result['timestamp'], \- result['raw_text'])+ result['text'])distribute_spk(sentence_list, sv_output)result['sentence_info'] = sentence_listelif kwargs.get("sentence_timestamp", False):sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \result['timestamp'], \- result['raw_text'])+ result['text'])result['sentence_info'] = sentence_list- del result['spk_embedding']+ if "spk_embedding" in result: del result['spk_embedding']result["key"] = keyresults_ret_list.append(result)diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.pyindex 129f834d0..b3c99539b 100644--- a/funasr/train_utils/trainer.py+++ b/funasr/train_utils/trainer.py@@ -279,7 +279,7 @@ class Trainer:f"epoch: {epoch}/{self.max_epoch}, "f"step: {batch_idx+1}/{len(self.dataloader_train)}, total: {self.batch_total}, "f"(loss: {loss.detach().cpu().item():.3f}), "- f"(lr: {lr}), "+ f"(lr: {lr:.3e}), "f"{[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]}, "f"{speed_stats}, "f"{gpu_info}"