decoding

游雁

2024-06-13 5de8bfdcd8a617ac13c13478505401bbf4e57472

 examples/industrial_data_pretraining/llm_asr/demo_speech2text.py

@@ -3,32 +3,49 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

import json
import os
import sys

from funasr import AutoModel

ckpt_dir = "/nfs/beinian.lzr/workspace/GPT-4o/Exp/exp6/5m-8gpu/exp6_speech2text_linear_ddp_0609"
ckpt_id = "model.pt.ep0.90000"
jsonl = (
    "/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]
jsonl = sys.argv[3]
output_dir = sys.argv[4]
device = sys.argv[5]

model = AutoModel(
    model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
    vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
    vad_kwargs={"max_single_segment_time": 60000},
    punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
    # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
    model=ckpt_dir,
    init_param=f"{os.path.join(ckpt_dir, ckpt_id)}",
    output_dir=output_dir,
    device=device,
    fp16=False,
    bf16=False,
    llm_dtype="bf16",
)

res = model.generate(
    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
    cache={},
)

print(res)
with open(jsonl, "r") as f:
    lines = f.readlines()

tearchforing = False
for i, line in enumerate(lines):
    data_dict = json.loads(line.strip())
    data = data_dict["messages"]

""" can not use currently
from funasr import AutoFrontend
    res = model.generate(
        input=[data],
        tearchforing=tearchforing,
        cache={},
    )

frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")

fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)

for batch_idx, fbank_dict in enumerate(fbanks):
    res = model.generate(**fbank_dict)
    print(res)
"""