fix bug

游雁

2024-06-09 7fc17b1aafb0c53ac83a86ecf4adbee3e10fdb86

fix bug

 examples/industrial_data_pretraining/llm_asr/demo_speech2text.py

@@ -15,6 +15,7 @@
    "/nfs/beinian.lzr/workspace/GPT-4o/Data/Speech2Text/TestData/aishell1_test_speech2text.jsonl"
)
output_dir = f"{os.path.join(ckpt_dir, ckpt_id)}"
device = "cuda:0"

ckpt_dir = sys.argv[1]
ckpt_id = sys.argv[2]

 examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh

@@ -1,10 +1,10 @@



ckpt_dir="/nfs/zhifu.gzf/ckpt/saves/qwen_1.5_7b/full/sft/asr_tts_text_exp1_ds_z3/checkpoint-11000"
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="${ckpt_dir}/asr"
out_dir="${ckpt_dir}/inference-${ckpt_id}"
mkdir -p ${out_dir}

device="cuda:0"
@@ -12,9 +12,9 @@
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}

    pred_file=${out_dir}/${data_set}/1best_recog/text_tn
    ref_file=${out_dir}/${data_set}/1best_recog/label
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label

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

@@ -26,9 +26,9 @@
for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}

    pred_file=${out_dir}/${data_set}/1best_recog/text_tn
    ref_file=${out_dir}/${data_set}/1best_recog/label
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label

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

@@ -39,9 +39,9 @@
for data_set in "s2tt_en2zh.v20240605.test.jsonl"; do
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}

    pred_file=${out_dir}/${data_set}/1best_recog/text_tn
    ref_file=${out_dir}/${data_set}/1best_recog/label
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label

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

@@ -52,9 +52,9 @@
for data_set in "s2tt_zh2en.v20240605.test.jsonl"; do
    jsonl=${jsonl_dir}/${data_set}
    output_dir=${out_dir}/${data_set}

    pred_file=${out_dir}/${data_set}/1best_recog/text_tn
    ref_file=${out_dir}/${data_set}/1best_recog/label
    mkdir -p ${output_dir}
    pred_file=${output_dir}/${data_set}/1best_recog/text_tn
    ref_file=${output_dir}/${data_set}/1best_recog/label

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


 funasr/models/llm_asr/model.py

@@ -556,7 +556,7 @@

        return contents

    def data_load_speech(self, contents: dict, tokenizer, frontend, **kwargs):
    def data_load_speech(self, contents: dict, tokenizer, frontend, meta_data={}, **kwargs):

        system = contents["system"]
        user = contents["user"]
@@ -594,7 +594,10 @@
                    )
                    if sub_str.startswith("!"):
                        try:
                            time1 = time.perf_counter()
                            data_src = load_audio_text_image_video(sub_str[1:], fs=frontend.fs)
                            time2 = time.perf_counter()
                            meta_data["load_data"] = f"{time2 - time1:0.3f}"
                        except Exception as e:
                            logging.error(f"Loading wav failed! {str(e)}, {traceback.format_exc()}")

@@ -604,6 +607,15 @@
                            frontend=frontend,
                            is_final=True,
                        )  # speech: [b, T, d]

                        time3 = time.perf_counter()
                        meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
                        meta_data["batch_data_time"] = (
                            speech_lengths.sum().item()
                            * frontend.frame_shift
                            * frontend.lfr_n
                            / 1000
                        )

                        if kwargs.get("permute", True):
                            speech = speech.permute(0, 2, 1)
@@ -666,7 +678,7 @@
            raise NotImplementedError("batch decoding is not implemented")

        contents = self.data_template(data_in[0])
        output = self.data_load_speech(contents, tokenizer, frontend, **kwargs)
        output = self.data_load_speech(contents, tokenizer, frontend, meta_data=meta_data, **kwargs)
        batch = to_device(output, kwargs["device"])

        # audio encoder