auto frontend

游雁

2024-06-06 6a7d34392c5cc3bdb512670aadb7847ae7916741

auto frontend

 examples/industrial_data_pretraining/llm_asr/conf/whisper_qwen_linear2.yaml

New file
@@ -0,0 +1,78 @@
# This is an example that demonstrates how to configure a model file.
# You can modify the configuration according to your own requirements.

# to print the register_table:
# from funasr.register import tables
# tables.print()

# network architecture
model: LLMASR2
model_conf:
    lsm_weight: 0.1     # label smoothing option
    length_normalized_loss: true

# encoder
audio_encoder: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope"
audio_encoder_conf:
    hub: ms
    freeze: true

llm: Qwen1.5-7b-chat
llm_conf:
  hub: hf
  freeze: true
  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"

audio_adaptor: Transformer
audio_adaptor_conf:
  downsample_rate: 2
  llm_dim: 4096
  encoder_dim: 1280
  n_layer: 2

# frontend related
frontend: WhisperFrontend
frontend_conf:
    fs: 16000
    whisper_model: large-v3
    do_pad_trim: true
    permute: false # true: [bs, frames, dims]; false: [bs, dims, frames]
    filters_path: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope/assets/mel_filters.npz"



train_conf:
  accum_grad: 1
  grad_clip: 5
  max_epoch: 15
  keep_nbest_models: 10
  log_interval: 10

optim: adamw
optim_conf:
   lr: 0.0001
   weight_decay: 0.000000

scheduler: warmuplr
scheduler_conf:
   warmup_steps: 1500

dataset: OpenAIDataset
dataset_conf:
    index_ds: OpenAIIndexDSJsonl
    batch_sampler: CustomDistributedBatchSampler
    batch_type: example # example or length
    batch_size: 4 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    max_token_length: 3000 # filter samples if source_token_len+target_token_len > max_token_length,
    shuffle: True
    num_workers: 0
    audio_adaptor_downsample_rate: ${audio_adaptor_conf.downsample_rate}
    audio_encoder_downsample_rate: 2
#    prompt: "<|startoftranscription|><|zh|><|transcribe|><|zh|><|notimestamps|><|wo_itn|>"



tokenizer: HuggingfaceTokenizer
tokenizer_conf:
  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"


 examples/industrial_data_pretraining/llm_asr/demo_train_or_finetune2.sh

New file
@@ -0,0 +1,46 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)


# which gpu to train or finetune
export CUDA_VISIBLE_DEVICES="0"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')

# data dir, which contains: train.json, val.json, tokens.jsonl/tokens.txt, am.mvn
#data_dir="/Users/zhifu/funasr1.0/data/list"

## generate jsonl from wav.scp and text.txt
#python -m funasr.datasets.audio_datasets.scp2jsonl \
#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
#++data_type_list='["source", "target"]' \
#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl

train_data="/nfs/beinian.lzr/workspace/tools/speech2speech_tools/speech2text/out_dir/tmp_wav.jsonl"
val_data="/nfs/beinian.lzr/workspace/tools/speech2speech_tools/speech2text/out_dir/tmp_wav.jsonl"

# exp output dir
output_dir="/Users/zhifu/funasr1.0/test_local/data_tmp/"
log_file="${output_dir}/log.txt"

workspace=`pwd`
config="whisper_qwen_linear2.yaml"

init_param="${output_dir}/model.pt"

mkdir -p ${output_dir}
echo "log_file: ${log_file}"

torchrun \
--nnodes 1 \
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
--config-path "${workspace}/conf" \
--config-name "${config}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset_conf.batch_size=1 \
++dataset_conf.num_workers=0 \
++train_conf.max_epoch=15 \
++optim_conf.lr=0.0001 \
++init_param="${init_param}" \
++output_dir="${output_dir}" &> ${log_file} &