End of training

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- fleurs
+model-index:
+- name: experiment
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# experiment
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the fleurs dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,267 @@
+{
+  "architectures": [
+    "JointCTCAttentionEncoderDecoder"
+  ],
+  "bos_token_id": 0,
+  "ctc_weight": 0.0,
+  "decoder": {
+    "_name_or_path": "Lakoc/gpt2_tiny_decoder_6_layers",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_embd": 256,
+    "n_head": 4,
+    "n_inner": 2048,
+    "n_layer": 6,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_size": 256,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "pos_emb_fixed": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 5000
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "Lakoc/fisher_ebranchformer_enc_12_layers_fixed",
+    "activation_dropout": 0.1,
+    "adapter_attn_dim": null,
+    "adapter_kernel_size": 3,
+    "adapter_stride": 2,
+    "add_adapter": false,
+    "add_cross_attention": false,
+    "apply_spec_augment": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "classifier_proj_size": 256,
+    "codevector_dim": 256,
+    "conformer_conv_dropout": 0.1,
+    "contrastive_logits_temperature": 0.1,
+    "conv_bias": false,
+    "conv_depthwise_kernel_size": 31,
+    "conv_dim": [
+      256,
+      256
+    ],
+    "conv_kernel": [
+      3,
+      3
+    ],
+    "conv_padding": [
+      1,
+      1
+    ],
+    "conv_stride": [
+      2,
+      2
+    ],
+    "cross_attention_hidden_size": null,
+    "csgu_activation": "identity",
+    "csgu_conv_dropout": 0.1,
+    "csgu_kernel_size": 31,
+    "csgu_use_linear_after_conv": false,
+    "ctc_loss_reduction": "mean",
+    "ctc_zero_infinity": true,
+    "decoder_start_token_id": null,
+    "diversity_loss_weight": 0.1,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "do_stable_layer_norm": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "fe_position_embeddings": false,
+    "feat_extract_activation": "gelu",
+    "feat_extract_norm": "group",
+    "feat_proj_dropout": 0.0,
+    "feat_quantizer_dropout": 0.0,
+    "final_dropout": 0.1,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "is_causal": false,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "max_length": 20,
+    "max_source_positions": 1024,
+    "merge_conv_kernel": 31,
+    "min_length": 0,
+    "model_type": "wav2vec2-ebranchformer",
+    "no_repeat_ngram_size": 0,
+    "num_adapter_layers": 3,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codevector_groups": 2,
+    "num_codevectors_per_group": 320,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_fbanks": 80,
+    "num_feat_extract_layers": 2,
+    "num_hidden_layers": 12,
+    "num_mel_bins": 80,
+    "num_negatives": 100,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_size": 256,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 3,
+    "position_embeddings_type": "relative",
+    "prefix": null,
+    "problem_type": null,
+    "proj_codevector_dim": 256,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rotary_embedding_base": 10000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "tdnn_dilation": [
+      1,
+      2,
+      3,
+      1,
+      1
+    ],
+    "tdnn_dim": [
+      512,
+      512,
+      512,
+      512,
+      1500
+    ],
+    "tdnn_kernel": [
+      5,
+      3,
+      3,
+      1,
+      1
+    ],
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_fbanks": true,
+    "use_macaron_ff": true,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 5000,
+    "xvector_output_dim": 512
+  },
+  "eos_token_id": 1,
+  "is_encoder_decoder": true,
+  "lsm_factor": 0,
+  "mask_token_id": 4,
+  "model_type": "joint_aed_ctc_speech-encoder-decoder",
+  "pad_token_id": 3,
+  "shared_lm_head": false,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3"
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "apply_eos_space_trick": false,
+  "bos_token_id": 0,
+  "ctc_margin": 0,
+  "ctc_weight": 0.3,
+  "decoder_start_token_id": 0,
+  "eos_space_trick_weight": 0.0,
+  "eos_token_id": 1,
+  "lm_model": null,
+  "lm_weight": 0.0,
+  "max_length": 2,
+  "num_beams": 10,
+  "pad_token_id": 3,
+  "space_token_id": -1,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca55c428454bb8ceb8ace429c0b0fe71f126814daa3c527d080282bb77b6736b
+size 155523256

predictions_test_wer100.00.csv

@@ -0,0 +1,3 @@
+label,prediction
+however due to the slow communication channels styles in the west could lag behind by 25 to 30 year,
+all nouns alongside the word sie for you always begin with a capital letter even in the middle of a sentence,

predictions_test_wer100.00_hyp.trn

@@ -0,0 +1,2 @@
+ (utterance_0)
+ (utterance_1)

predictions_test_wer100.00_hyp.trn.dtl

@@ -0,0 +1,107 @@
+DETAILED OVERALL REPORT FOR THE SYSTEM: experiment/predictions_test_wer100.00_hyp.trn
+
+SENTENCE RECOGNITION PERFORMANCE
+
+ sentences                                           2
+ with errors                            100.0%   (   2)
+
+   with substitutions                     0.0%   (   0)
+   with deletions                       100.0%   (   2)
+   with insertions                        0.0%   (   0)
+
+
+WORD RECOGNITION PERFORMANCE
+
+Percent Total Error       =  100.0%   (  40)
+
+Percent Correct           =    0.0%   (   0)
+
+Percent Substitution      =    0.0%   (   0)
+Percent Deletions         =  100.0%   (  40)
+Percent Insertions        =    0.0%   (   0)
+Percent Word Accuracy     =    0.0%
+
+
+Ref. words                =           (  40)
+Hyp. words                =           (   0)
+Aligned words             =           (  40)
+
+CONFUSION PAIRS                  Total                 (0)
+                                 With >=  1 occurrences (0)
+
+     -------
+         0
+
+
+
+INSERTIONS                       Total                 (0)
+                                 With >=  1 occurrences (0)
+
+     -------
+         0
+
+
+
+DELETIONS                        Total                 (34)
+                                 With >=  1 occurrences (34)
+
+   1:    4  ->  the
+   2:    2  ->  a
+   3:    2  ->  in
+   4:    2  ->  to
+   5:    1  ->  25
+   6:    1  ->  30
+   7:    1  ->  all
+   8:    1  ->  alongside
+   9:    1  ->  always
+  10:    1  ->  begin
+  11:    1  ->  behind
+  12:    1  ->  by
+  13:    1  ->  capital
+  14:    1  ->  channels
+  15:    1  ->  communication
+  16:    1  ->  could
+  17:    1  ->  due
+  18:    1  ->  even
+  19:    1  ->  for
+  20:    1  ->  however
+  21:    1  ->  lag
+  22:    1  ->  letter
+  23:    1  ->  middle
+  24:    1  ->  nouns
+  25:    1  ->  of
+  26:    1  ->  sentence
+  27:    1  ->  sie
+  28:    1  ->  slow
+  29:    1  ->  styles
+  30:    1  ->  west
+  31:    1  ->  with
+  32:    1  ->  word
+  33:    1  ->  year
+  34:    1  ->  you
+     -------
+        40
+
+
+
+SUBSTITUTIONS                    Total                 (0)
+                                 With >=  1 occurrences (0)
+
+     -------
+         0
+
+
+* NOTE: The 'Substitution' words are those reference words
+        for which the recognizer supplied an incorrect word.
+
+
+FALSELY RECOGNIZED               Total                 (0)
+                                 With >=  1 occurrences (0)
+
+     -------
+         0
+
+
+* NOTE: The 'Falsely Recognized' words are those hypothesis words
+        which the recognizer incorrectly substituted for a reference word.
+

predictions_test_wer100.00_hyp.trn.snt.utt

@@ -0,0 +1,47 @@
+===============================================================================
+
+                     SENTENCE LEVEL REPORT FOR THE SYSTEM:
+    Name: experiment/predictions_test_wer100.00_hyp.trn
+
+===============================================================================
+
+
+SPEAKER utt
+id: (utterance_0)
+Scores: (#C #S #D #I) 0 0 19 0
+REF:  HOWEVER DUE TO THE SLOW COMMUNICATION CHANNELS STYLES IN THE WEST COULD LAG BEHIND BY 25 TO 30 YEAR 
+HYP:  ******* *** ** *** **** ************* ******** ****** ** *** **** ***** *** ****** ** ** ** ** **** 
+Eval: D       D   D  D   D    D             D        D      D  D   D    D     D   D      D  D  D  D  D    
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =    0.0%    0   (  0)
+Deletions             =  100.0%   19   ( 19)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =  100.0%   19   ( 19)
+
+Ref. words            =           19   ( 19)
+Hyp. words            =            0   (  0)
+Aligned words         =           19   ( 19)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_1)
+Scores: (#C #S #D #I) 0 0 21 0
+REF:  ALL NOUNS ALONGSIDE THE WORD SIE FOR YOU ALWAYS BEGIN WITH A CAPITAL LETTER EVEN IN THE MIDDLE OF A SENTENCE 
+HYP:  *** ***** ********* *** **** *** *** *** ****** ***** **** * ******* ****** **** ** *** ****** ** * ******** 
+Eval: D   D     D         D   D    D   D   D   D      D     D    D D       D      D    D  D   D      D  D D        
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =    0.0%    0   (  0)
+Deletions             =  100.0%   21   ( 40)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =  100.0%   21   ( 40)
+
+Ref. words            =           21   ( 40)
+Hyp. words            =            0   (  0)
+Aligned words         =           21   ( 40)
+
+-------------------------------------------------------------------------------
+

predictions_test_wer100.00_hyp.trn.sys

@@ -0,0 +1,18 @@
+
+
+
+                     SYSTEM SUMMARY PERCENTAGES by SPEAKER                      
+
+       ,----------------------------------------------------------------.
+       |         experiment/predictions_test_wer100.00_hyp.trn          |
+       |----------------------------------------------------------------|
+       | SPKR   | # Snt # Wrd | Corr    Sub    Del    Ins    Err  S.Err |
+       |--------+-------------+-----------------------------------------|
+       | utt    |    2     40 |  0.0    0.0  100.0    0.0  100.0  100.0 |
+       |================================================================|
+       | Sum/Avg|    2     40 |  0.0    0.0  100.0    0.0  100.0  100.0 |
+       |================================================================|
+       |  Mean  |  2.0   40.0 |  0.0    0.0  100.0    0.0  100.0  100.0 |
+       |  S.D.  |  0.0    0.0 |  0.0    0.0    0.0    0.0    0.0    0.0 |
+       | Median |  2.0   40.0 |  0.0    0.0  100.0    0.0  100.0  100.0 |
+       `----------------------------------------------------------------'

predictions_test_wer100.00_ref.trn

@@ -0,0 +1,2 @@
+however due to the slow communication channels styles in the west could lag behind by 25 to 30 year (utterance_0)
+all nouns alongside the word sie for you always begin with a capital letter even in the middle of a sentence (utterance_1)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785595cebe6a6659364634617201e4fe23ae8d931b537c009a48cc36375351f9
+size 5496