add ctc inference code (#1806)

zhifu gao

2024-06-11 997374b88fe6b2ae5cb4dcaf47d78cb3eff09fc2

 examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh

@@ -1,20 +1,22 @@



ckpt_dir="/nfs/beinian.lzr/workspace/GPT-4o/Exp/exp6/5m-8gpu/exp6_speech2text_linear_ddp_0609"
ckpt_id="model.pt.ep0.90000"
jsonl_dir="/nfs/beinian.lzr/workspace/GPT-4o/Data/Speech2Text/TestData"
out_dir="${ckpt_dir}/inference-${ckpt_id}"
mkdir -p ${out_dir}

device="cuda:0"

ckpt_id=$1
device=$2

ckpt_dir="/nfs/beinian.lzr/workspace/GPT-4o/Exp/exp6/5m-8gpu/exp6_speech2text_linear_ddp_0609"
jsonl_dir="/nfs/beinian.lzr/workspace/GPT-4o/Data/Speech2Text/TestData"

out_dir="${ckpt_dir}/inference-${ckpt_id}"
mkdir -p ${out_dir}
for data_set in "librispeech_test_clean_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label
    pred_file=${output_dir}/1best_recog/text_tn
    ref_file=${output_dir}/1best_recog/label

    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}

@@ -27,10 +29,10 @@
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label
    pred_file=${output_dir}/1best_recog/text_tn
    ref_file=${output_dir}/1best_recog/label

    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}

    python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true

@@ -40,10 +42,10 @@
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label
    pred_file=${output_dir}/1best_recog/text_tn
    ref_file=${output_dir}/1best_recog/label

    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}

    python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true

@@ -53,11 +55,11 @@
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label
    pred_file=${output_dir}/1best_recog/text_tn
    ref_file=${output_dir}/1best_recog/label

    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
    python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}

    python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true
    python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=false

done