Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ms_upload_cache +1 -0
- .ms_upload_progress +1 -0
- dolphin_fangyan_feature_poster_v3.png +3 -0
- global_cmvn +1 -0
- small.fangyan.prompt.pt +3 -0
- train.yaml +120 -0
- units.txt +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
dolphin_fangyan_feature_poster_v3.png filter=lfs diff=lfs merge=lfs -text
|
.ms_upload_cache
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train.yaml|1778053457.6800096|2418": {"file_hash": "e996478969385586d2bb241372a3e1d58a3252f97c45f5ad60d18a17d9f09c9e", "file_size": 2418}, "global_cmvn|1778053457.679033|2215": {"file_hash": "b1d75d6230fbbd34ae8eefc2f2488cfcb28b9894af7f14f27dc1576f081258f3", "file_size": 2215}, "dolphin_fangyan_feature_poster_v3.png|1778143130.1857708|586543": {"file_hash": "fd337571c3573b3aeff3891045074b2efe3a98017452e9fdd8fcfd986bb2c884", "file_size": 586543}, "units.txt|1778053457.677791|204069": {"file_hash": "0f146c2fa2009c6ddea13449976acf6ab5738f88af8634db23b1946bd78250cd", "file_size": 204069}, "small.fangyan.prompt.pt|1778053457.6650314|1545489889": {"file_hash": "fdd09034024fc3aee16c89f678461791b2eb4ac0ae880da4ea6141e0e32f409b", "file_size": 1545489889}}
|
.ms_upload_progress
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"repo_id": "DataoceanAI/dolphin-small-fangyan-prompt", "batch_fingerprints": {"0": "e950e90b0a85f2fdb1897082e20a0df8a83ff7c60336dd5707c48b3cc77e34e4"}, "committed_batches": [0]}
|
dolphin_fangyan_feature_poster_v3.png
ADDED
|
Git LFS Details
|
global_cmvn
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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.prompt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd09034024fc3aee16c89f678461791b2eb4ac0ae880da4ea6141e0e32f409b
|
| 3 |
+
size 1545489889
|
train.yaml
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
accum_grad: 4
|
| 2 |
+
cmvn: global_cmvn
|
| 3 |
+
cmvn_conf:
|
| 4 |
+
cmvn_file: data/train/global_cmvn
|
| 5 |
+
is_json_cmvn: true
|
| 6 |
+
ctc: ctc
|
| 7 |
+
ctc_conf:
|
| 8 |
+
ctc_blank_id: 0
|
| 9 |
+
dataset: asr
|
| 10 |
+
dataset_conf:
|
| 11 |
+
batch_conf:
|
| 12 |
+
batch_size: 20
|
| 13 |
+
batch_type: static
|
| 14 |
+
ctc_label: true
|
| 15 |
+
cycle: 100
|
| 16 |
+
fbank_conf:
|
| 17 |
+
dither: 0.1
|
| 18 |
+
frame_length: 25
|
| 19 |
+
frame_shift: 10
|
| 20 |
+
num_mel_bins: 80
|
| 21 |
+
filter_conf:
|
| 22 |
+
max_length: 3000
|
| 23 |
+
min_length: 0
|
| 24 |
+
token_max_length: 200
|
| 25 |
+
token_min_length: 1
|
| 26 |
+
no_time_idx: 3
|
| 27 |
+
prompt_conf:
|
| 28 |
+
context_conf:
|
| 29 |
+
batch_num_context: 60
|
| 30 |
+
len_max: 5
|
| 31 |
+
len_min: 2
|
| 32 |
+
utt_num_context: 3
|
| 33 |
+
prompt_conf:
|
| 34 |
+
max_number_out_prompts: 4
|
| 35 |
+
noprompt_prob: 0.4
|
| 36 |
+
prompt_tokens:
|
| 37 |
+
end: <PROMPT_END>
|
| 38 |
+
start: <PROMPT_START>
|
| 39 |
+
remove_punctuation: true
|
| 40 |
+
remove_timestamp: true
|
| 41 |
+
resample_conf:
|
| 42 |
+
resample_rate: 16000
|
| 43 |
+
shuffle: true
|
| 44 |
+
shuffle_conf:
|
| 45 |
+
shuffle_size: 2048
|
| 46 |
+
sort: true
|
| 47 |
+
sort_conf:
|
| 48 |
+
sort_size: 2048
|
| 49 |
+
spec_aug: true
|
| 50 |
+
spec_aug_conf:
|
| 51 |
+
max_f: 10
|
| 52 |
+
max_t: 50
|
| 53 |
+
num_f_mask: 2
|
| 54 |
+
num_t_mask: 2
|
| 55 |
+
speed_perturb: true
|
| 56 |
+
time_apply_prob: 0.0
|
| 57 |
+
decoder: transformer
|
| 58 |
+
decoder_conf:
|
| 59 |
+
attention_heads: 12
|
| 60 |
+
dropout_rate: 0.1
|
| 61 |
+
linear_units: 3072
|
| 62 |
+
num_blocks: 12
|
| 63 |
+
positional_dropout_rate: 0.1
|
| 64 |
+
self_attention_dropout_rate: 0.1
|
| 65 |
+
src_attention_dropout_rate: 0.1
|
| 66 |
+
use_sdpa: true
|
| 67 |
+
dtype: fp32
|
| 68 |
+
encoder: e_branchformer
|
| 69 |
+
encoder_conf:
|
| 70 |
+
activation_type: swish
|
| 71 |
+
attention_dropout_rate: 0.1
|
| 72 |
+
attention_heads: 12
|
| 73 |
+
causal: false
|
| 74 |
+
cgmlp_conv_kernel: 31
|
| 75 |
+
cgmlp_linear_units: 3072
|
| 76 |
+
dropout_rate: 0.1
|
| 77 |
+
gate_activation: identity
|
| 78 |
+
input_layer: conv2d
|
| 79 |
+
linear_units: 3072
|
| 80 |
+
merge_conv_kernel: 31
|
| 81 |
+
num_blocks: 12
|
| 82 |
+
output_size: 768
|
| 83 |
+
pos_enc_layer_type: rel_pos
|
| 84 |
+
positional_dropout_rate: 0.1
|
| 85 |
+
selfattention_layer_type: rel_selfattn
|
| 86 |
+
use_linear_after_conv: false
|
| 87 |
+
use_sdpa: true
|
| 88 |
+
grad_clip: 5
|
| 89 |
+
input_dim: 80
|
| 90 |
+
log_interval: 10
|
| 91 |
+
max_epoch: 100
|
| 92 |
+
model: asr_model
|
| 93 |
+
model_conf:
|
| 94 |
+
ctc_weight: 0.2
|
| 95 |
+
length_normalized_loss: false
|
| 96 |
+
lsm_weight: 0.1
|
| 97 |
+
model_dir: exp/dolphin_ebf_small_nostreaming_prompt
|
| 98 |
+
optim: adam
|
| 99 |
+
optim_conf:
|
| 100 |
+
lr: 0.0005
|
| 101 |
+
output_dim: 18173
|
| 102 |
+
save_interval: 200
|
| 103 |
+
save_states: model_only
|
| 104 |
+
scheduler: warmuplr
|
| 105 |
+
scheduler_conf:
|
| 106 |
+
warmup_steps: 2048
|
| 107 |
+
stats_dialect: true
|
| 108 |
+
tokenizer: char
|
| 109 |
+
tokenizer_conf:
|
| 110 |
+
special_tokens:
|
| 111 |
+
<asr>: 4
|
| 112 |
+
<blank>: 0
|
| 113 |
+
<eos>: 3
|
| 114 |
+
<sos>: 2
|
| 115 |
+
<unk>: 1
|
| 116 |
+
split_with_space: false
|
| 117 |
+
symbol_table_path: data/dict/units.txt
|
| 118 |
+
train_engine: torch_ddp
|
| 119 |
+
use_amp: false
|
| 120 |
+
vocab_size: 18173
|
units.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|