Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dolphin_fangyan_feature_poster_v3.png filter=lfs diff=lfs merge=lfs -text

.ms_upload_cache

@@ -0,0 +1 @@
+{"global_cmvn|1778053465.497586|2215": {"file_hash": "b1d75d6230fbbd34ae8eefc2f2488cfcb28b9894af7f14f27dc1576f081258f3", "file_size": 2215}, "train.yaml|1778053463.4532516|2511": {"file_hash": "cad5f3cf294f6e782ebbbfbdc6fa915dd28d58747725bccba1eb21e4d0320758", "file_size": 2511}, "units.txt|1778053465.4964416|204080": {"file_hash": "ae30a90c348326c2d25806509880aca20eac22317d1ece24a7b49b496301c0a8", "file_size": 204080}, "dolphin_fangyan_feature_poster_v3.png|1778143127.128445|586543": {"file_hash": "fd337571c3573b3aeff3891045074b2efe3a98017452e9fdd8fcfd986bb2c884", "file_size": 586543}, "small.fangyan.streaming.pt|1778053465.4930758|1775332955": {"file_hash": "bba8688ed33841b5f8b4578370be553f4557739c406dc7298f22985f7b061faf", "file_size": 1775332955}}

.ms_upload_progress

@@ -0,0 +1 @@
+{"repo_id": "DataoceanAI/dolphin-small-fangyan-streaming", "batch_fingerprints": {"0": "70ea7666210958b54f75d5921c5a918190152d4fa6d1fdf98916e9a6bc6d4bd2"}, "committed_batches": [0]}

global_cmvn

@@ -0,0 +1 @@
+{"mean_stat": [533749120.0, 537379776.0, 553561472.0, 587164544.0, 631869696.0, 662598848.0, 684377024.0, 695393728.0, 692471168.0, 679433984.0, 666123200.0, 656323712.0, 665752576.0, 678693440.0, 681920896.0, 679622080.0, 669891840.0, 656595136.0, 653838528.0, 637679232.0, 628412096.0, 644836864.0, 638840960.0, 646180608.0, 639724352.0, 642756992.0, 637471744.0, 642369856.0, 643414976.0, 647382848.0, 649348672.0, 649294336.0, 650233920.0, 654485056.0, 660473792.0, 667416512.0, 673158464.0, 675675200.0, 675123648.0, 668017536.0, 670060160.0, 662626240.0, 663143808.0, 662504064.0, 666413696.0, 672262080.0, 678483904.0, 685386048.0, 692572416.0, 699064000.0, 700785280.0, 701202688.0, 702666560.0, 705441664.0, 706070720.0, 705989248.0, 702842816.0, 699316416.0, 696090176.0, 687561152.0, 675279808.0, 663676352.0, 662962880.0, 664298944.0, 666095808.0, 671681664.0, 676652224.0, 680097152.0, 683811072.0, 688700992.0, 692082880.0, 695787904.0, 701085376.0, 706388736.0, 711491584.0, 717637248.0, 719691456.0, 715812736.0, 696362624.0, 604648448.0], "var_stat": [5413307392.0, 5559845888.0, 6150984704.0, 6921248256.0, 7999779840.0, 8789867520.0, 9405782016.0, 9768041472.0, 9759789056.0, 9430661120.0, 9090545664.0, 8873148416.0, 9155918848.0, 9542536192.0, 9653540864.0, 9593434112.0, 9316643840.0, 8959277056.0, 8863545344.0, 8450634752.0, 8211585536.0, 8587086336.0, 8432618496.0, 8583947264.0, 8401719808.0, 8439344640.0, 8293782528.0, 8401505280.0, 8427503104.0, 8525163520.0, 8577082880.0, 8575110656.0, 8594999296.0, 8701685760.0, 8854966272.0, 9029483520.0, 9168757760.0, 9221463040.0, 9194539008.0, 8997074944.0, 9024589824.0, 8819394560.0, 8807888896.0, 8777241600.0, 8869670912.0, 9017397248.0, 9173403648.0, 9345572864.0, 9530641408.0, 9701232640.0, 9748996096.0, 9762760704.0, 9801994240.0, 9874428928.0, 9883272192.0, 9873506304.0, 9780680704.0, 9672627200.0, 9569440768.0, 9321866240.0, 8968148992.0, 8646342656.0, 8616977408.0, 8648623104.0, 8702088192.0, 8859208704.0, 8999405568.0, 9105936384.0, 9220425728.0, 9358615552.0, 9451428864.0, 9552728064.0, 9695461376.0, 9836660736.0, 9970957312.0, 10135880704.0, 10189387776.0, 10070480896.0, 9532967936.0, 7261238272.0], "frame_num": 54068199}

small.fangyan.streaming.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba8688ed33841b5f8b4578370be553f4557739c406dc7298f22985f7b061faf
+size 1775332955

train.yaml

@@ -0,0 +1,125 @@
+accum_grad: 4
+cmvn: global_cmvn
+cmvn_conf:
+  cmvn_file: data/train/global_cmvn
+  is_json_cmvn: true
+context_module: cppn
+context_module_conf:
+  attention_heads: 4
+  dropout_rate: 0.1
+  embedding_size: 768
+  encoder_layers: 2
+ctc: ctc
+ctc_conf:
+  ctc_blank_id: 0
+dataset: asr
+dataset_conf:
+  batch_conf:
+    batch_size: 64
+    batch_type: static
+  context_conf:
+    batch_num_context: 200
+    len_max: 5
+    len_min: 2
+    mode: train
+    utt_num_context: 3
+  ctc_label: true
+  cycle: 100
+  fbank_conf:
+    dither: 0.1
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  filter_conf:
+    max_length: 3000
+    min_length: 0
+    token_max_length: 200
+    token_min_length: 1
+  no_time_idx: 3
+  remove_punctuation: true
+  remove_timestamp: true
+  resample_conf:
+    resample_rate: 16000
+  shuffle: true
+  shuffle_conf:
+    shuffle_size: 1024
+  sort: true
+  sort_conf:
+    sort_size: 1024
+  spec_aug: true
+  spec_aug_conf:
+    max_f: 10
+    max_t: 50
+    num_f_mask: 2
+    num_t_mask: 2
+  spec_trim: true
+  spec_trim_conf:
+    max_t: 30
+  speed_perturb: false
+  time_apply_prob: 0.0
+decoder: transformer
+decoder_conf:
+  attention_heads: 12
+  dropout_rate: 0.1
+  linear_units: 3072
+  num_blocks: 12
+  positional_dropout_rate: 0.1
+  self_attention_dropout_rate: 0.1
+  src_attention_dropout_rate: 0.1
+  use_sdpa: true
+dtype: fp32
+encoder: e_branchformer
+encoder_conf:
+  activation_type: swish
+  attention_dropout_rate: 0.1
+  attention_heads: 12
+  causal: true
+  cgmlp_conv_kernel: 31
+  cgmlp_linear_units: 3072
+  dropout_rate: 0.1
+  gate_activation: identity
+  input_layer: conv2d
+  linear_units: 3072
+  merge_conv_kernel: 31
+  num_blocks: 12
+  output_size: 768
+  pos_enc_layer_type: rel_pos
+  positional_dropout_rate: 0.1
+  selfattention_layer_type: rel_selfattn
+  use_dynamic_chunk: true
+  use_dynamic_left_chunk: false
+  use_linear_after_conv: false
+  use_sdpa: true
+grad_clip: 5
+input_dim: 80
+log_interval: 20
+max_epoch: 100
+model: asr_model
+model_conf:
+  ctc_weight: 0.3
+  length_normalized_loss: false
+  lsm_weight: 0.1
+model_dir: exp/dolphin_ebf_small_streaming_bias_share_ctc_sample
+optim: adam
+optim_conf:
+  lr: 0.0005
+output_dim: 18173
+save_interval: 200
+save_states: model_only
+scheduler: warmuplr
+scheduler_conf:
+  warmup_steps: 2048
+stats_dialect: true
+tokenizer: char
+tokenizer_conf:
+  special_tokens:
+    <asr>: 4
+    <blank>: 0
+    <eos>: 3
+    <sos>: 2
+    <unk>: 1
+  split_with_space: false
+  symbol_table_path: data/dict/units.txt
+train_engine: torch_ddp
+use_amp: false
+vocab_size: 18173