update

游雁

2024-02-20 362a6de3c850079ed2ae6f94181f2a51c0596527

update

 examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml

@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: DynamicBatchLocalShuffleSampler
    batch_sampler: RankFullLocalShuffleBatchSampler
    batch_type: example # example or length
    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    batch_size: 32 # 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: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
    buffer_size: 500
    buffer_size: 1024
    shuffle: True
    num_workers: 4
    preprocessor_speech: SpeechPreprocessSpeedPerturb
    preprocessor_speech_conf:
      speed_perturb: [0.9, 1.0, 1.1]

tokenizer: CharTokenizer
tokenizer_conf:

 examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml

@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: DynamicBatchLocalShuffleSampler
    batch_sampler: RankFullLocalShuffleBatchSampler
    batch_type: example # example or length
    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    batch_size: 32 # 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: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
    buffer_size: 500
    buffer_size: 1024
    shuffle: True
    num_workers: 4
    preprocessor_speech: SpeechPreprocessSpeedPerturb
    preprocessor_speech_conf:
      speed_perturb: [0.9, 1.0, 1.1]

tokenizer: CharTokenizer
tokenizer_conf:

 examples/aishell/conformer/run.sh

@@ -109,9 +109,14 @@
  echo "log_file: ${log_file}"

  gpu_num=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
  torchrun \
  --nnodes 1 \
  --nproc_per_node ${gpu_num} \
#  torchrun \
#  --nnodes 1 \
#  --nproc_per_node ${gpu_num}
  cmd="python"
  if [ ${gpu_num} -gt 1  ];then
    cmd="torchrun --nnodes 1 --nproc_per_node ${gpu_num}"
  fi
  ${cmd} \
  ../../../funasr/bin/train.py \
  --config-path "${workspace}/conf" \
  --config-name "${config}" \

 examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml

@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: DynamicBatchLocalShuffleSampler
    batch_sampler: RankFullLocalShuffleBatchSampler
    batch_type: example # example or length
    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    batch_size: 32 # 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: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
    buffer_size: 500
    buffer_size: 1024
    shuffle: True
    num_workers: 4
    preprocessor_speech: SpeechPreprocessSpeedPerturb
    preprocessor_speech_conf:
      speed_perturb: [0.9, 1.0, 1.1]

tokenizer: CharTokenizer
tokenizer_conf:

 examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml

File was renamed from examples/aishell/transformer/transformer_12e_6d_2048_256.yaml
@@ -88,13 +88,16 @@
dataset: AudioDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: DynamicBatchLocalShuffleSampler
    batch_sampler: RankFullLocalShuffleBatchSampler
    batch_type: example # example or length
    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    batch_size: 32 # 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: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
    buffer_size: 500
    buffer_size: 1024
    shuffle: True
    num_workers: 0
    num_workers: 4
    preprocessor_speech: SpeechPreprocessSpeedPerturb
    preprocessor_speech_conf:
      speed_perturb: [0.9, 1.0, 1.1]

tokenizer: CharTokenizer
tokenizer_conf: