End of training

.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
+predictions_common_voice_13_en_common_voice_13_en_test_wer26.31_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_13_0
+metrics:
+- wer
+model-index:
+- name: DeCRED_small_cv
+  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. -->
+
+# DeCRED_small_cv
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_13_0 dataset.
+It achieves the following results on the evaluation set:
+- Cer: 0.0855
+- Deletions: 4133
+- Hits: 123172
+- Insertions: 3671
+- Loss: 1.1174
+- Mer: 0.1889
+- Substitutions: 20876
+- Wer: 0.1935
+- Wil: 0.3069
+- Wip: 0.6931
+
+## 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: 0.002
+- train_batch_size: 256
+- eval_batch_size: 128
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 512
+- total_eval_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10000
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Cer    | Deletions | Hits   | Insertions | Validation Loss | Mer    | Substitutions | Wer    | Wil    | Wip    |
+|:-------------:|:-----:|:-----:|:------:|:---------:|:------:|:----------:|:---------------:|:------:|:-------------:|:------:|:------:|:------:|
+| 1.3459        | 5.0   | 7445  | 0.1676 | 7277      | 102705 | 6830       | 1.5193          | 0.3374 | 38199         | 0.3530 | 0.5182 | 0.4818 |
+| 1.3006        | 6.0   | 8934  | 0.1584 | 6381      | 105485 | 7074       | 1.4779          | 0.3206 | 36315         | 0.3359 | 0.4956 | 0.5044 |
+| 1.7549        | 7.0   | 10423 | 0.1620 | 6967      | 104307 | 6557       | 1.4874          | 0.3259 | 36907         | 0.3403 | 0.5031 | 0.4969 |
+| 1.5621        | 8.0   | 11912 | 0.1361 | 5203      | 111002 | 6489       | 1.3687          | 0.2823 | 31976         | 0.2947 | 0.4437 | 0.5563 |
+| 1.4988        | 9.0   | 13401 | 0.1298 | 5025      | 112303 | 6136       | 1.3308          | 0.2723 | 30853         | 0.2835 | 0.4299 | 0.5701 |
+| 1.4495        | 10.0  | 14890 | 0.1212 | 5505      | 113957 | 5063       | 1.2901          | 0.2564 | 28719         | 0.2651 | 0.4068 | 0.5932 |
+| 1.4092        | 11.0  | 16379 | 0.1158 | 5162      | 115248 | 4910       | 1.2625          | 0.2472 | 27771         | 0.2554 | 0.3941 | 0.6059 |
+| 1.3638        | 12.0  | 17868 | 0.1088 | 4408      | 117314 | 5173       | 1.2336          | 0.2350 | 26459         | 0.2432 | 0.3764 | 0.6236 |
+| 1.335         | 13.0  | 19357 | 0.1060 | 4868      | 117783 | 4467       | 1.2177          | 0.2284 | 25530         | 0.2353 | 0.3665 | 0.6335 |
+| 1.2966        | 14.0  | 20846 | 0.1006 | 4561      | 119385 | 4599       | 1.1945          | 0.2186 | 24235         | 0.2254 | 0.3511 | 0.6489 |
+| 1.2826        | 15.0  | 22335 | 0.0969 | 4455      | 119983 | 4111       | 1.1767          | 0.2122 | 23743         | 0.2180 | 0.3429 | 0.6571 |
+| 1.2529        | 16.0  | 23824 | 0.0954 | 4229      | 120627 | 4312       | 1.1664          | 0.2090 | 23325         | 0.2150 | 0.3377 | 0.6623 |
+| 1.2103        | 17.0  | 25313 | 0.0907 | 4218      | 121711 | 3998       | 1.1458          | 0.2002 | 22252         | 0.2056 | 0.3244 | 0.6756 |
+| 1.18          | 18.0  | 26802 | 0.0891 | 4153      | 122139 | 3883       | 1.1355          | 0.1968 | 21889         | 0.2019 | 0.3194 | 0.6806 |
+| 1.1529        | 19.0  | 28291 | 0.0864 | 4132      | 122860 | 3681       | 1.1236          | 0.1910 | 21189         | 0.1957 | 0.3105 | 0.6895 |
+| 1.1342        | 20.0  | 29780 | 0.0855 | 4133      | 123172 | 3671       | 1.1174          | 0.1889 | 20876         | 0.1935 | 0.3069 | 0.6931 |
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.0+rocm5.6
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,275 @@
+{
+  "architectures": [
+    "JointCTCAttentionEncoderDecoder"
+  ],
+  "bos_token_id": 0,
+  "ctc_weight": 0.3,
+  "decoder": {
+    "_name_or_path": "Lakoc/gpt2_256h_6l_add_head3_04",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attn_pdrop": 0.1,
+    "average_logits": false,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "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": 1,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_locations": [
+      3
+    ],
+    "head_weights": [
+      0.6,
+      0.4
+    ],
+    "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-multi-head",
+    "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_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_additional_weights": 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": 1000
+  },
+  "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": 1000,
+    "xvector_output_dim": 512
+  },
+  "eos_token_id": 1,
+  "is_encoder_decoder": true,
+  "lsm_factor": 0.1,
+  "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": "4.40.0.dev0"
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "apply_eos_space_trick": false,
+  "bos_token_id": 0,
+  "ctc_margin": 0,
+  "ctc_weight": 0.0,
+  "decoder_start_token_id": 0,
+  "eos_space_trick_weight": 0.0,
+  "eos_token_id": 1,
+  "lm_model": null,
+  "lm_weight": 0.0,
+  "max_length": 512,
+  "pad_token_id": 3,
+  "space_token_id": -1,
+  "transformers_version": "4.40.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497190bb024e75b6d0e560b39282d01acefc76355f3940c66b2ac852a3d3a9c5
+size 144243216

predictions_common_voice_13_en_common_voice_13_en_test_wer100.00.csv

@@ -0,0 +1,5 @@
+label,prediction
+joe keaton disapproved of films and buster also had reservations about the medium,
+shell be all right,
+six,
+alls well that ends well,

predictions_common_voice_13_en_common_voice_13_en_test_wer100.00_hyp.trn

@@ -0,0 +1,4 @@
+ (utterance_0)
+ (utterance_1)
+ (utterance_2)
+ (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer100.00_ref.trn

@@ -0,0 +1,4 @@
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_0)
+shell be all right (utterance_1)
+six (utterance_2)
+alls well that ends well (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70.csv

@@ -0,0 +1,5 @@
+label,prediction
+joe keaton disapproved of films and buster also had reservations about the medium,a was available moa moas thea ends theas thels thes
+shell be all right,hus
+six,asasas theaslsas thes
+alls well that ends well,a wasasasasasaslasasasas californias alsasls alsas

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn

@@ -0,0 +1,4 @@
+a was available moa moas thea ends theas thels thes (utterance_0)
+hus (utterance_1)
+asasas theaslsas thes (utterance_2)
+a wasasasasasaslasasasas californias alsasls alsas (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn.dtl

@@ -0,0 +1,129 @@
+DETAILED OVERALL REPORT FOR THE SYSTEM: /scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn
+
+SENTENCE RECOGNITION PERFORMANCE
+
+ sentences                                           4
+ with errors                            100.0%   (   4)
+
+   with substitutions                   100.0%   (   4)
+   with deletions                        50.0%   (   2)
+   with insertions                       25.0%   (   1)
+
+
+WORD RECOGNITION PERFORMANCE
+
+Percent Total Error       =  108.7%   (  25)
+
+Percent Correct           =    0.0%   (   0)
+
+Percent Substitution      =   73.9%   (  17)
+Percent Deletions         =   26.1%   (   6)
+Percent Insertions        =    8.7%   (   2)
+Percent Word Accuracy     =   -8.7%
+
+
+Ref. words                =           (  23)
+Hyp. words                =           (  19)
+Aligned words             =           (  25)
+
+CONFUSION PAIRS                  Total                 (17)
+                                 With >=  1 occurrences (17)
+
+   1:    1  ->  about ==> theas
+   2:    1  ->  alls ==> a
+   3:    1  ->  also ==> moas
+   4:    1  ->  and ==> available
+   5:    1  ->  buster ==> moa
+   6:    1  ->  ends ==> alsasls
+   7:    1  ->  films ==> was
+   8:    1  ->  had ==> thea
+   9:    1  ->  medium ==> thes
+  10:    1  ->  of ==> a
+  11:    1  ->  reservations ==> ends
+  12:    1  ->  right ==> hus
+  13:    1  ->  six ==> thes
+  14:    1  ->  that ==> californias
+  15:    1  ->  the ==> thels
+  16:    1  ->  well ==> alsas
+  17:    1  ->  well ==> wasasasasasaslasasasas
+     -------
+        17
+
+
+
+INSERTIONS                       Total                 (2)
+                                 With >=  1 occurrences (2)
+
+   1:    1  ->  asasas
+   2:    1  ->  theaslsas
+     -------
+         2
+
+
+
+DELETIONS                        Total                 (6)
+                                 With >=  1 occurrences (6)
+
+   1:    1  ->  all
+   2:    1  ->  be
+   3:    1  ->  disapproved
+   4:    1  ->  joe
+   5:    1  ->  keaton
+   6:    1  ->  shell
+     -------
+         6
+
+
+
+SUBSTITUTIONS                    Total                 (16)
+                                 With >=  1 occurrences (16)
+
+   1:    2  ->  well
+   2:    1  ->  about
+   3:    1  ->  alls
+   4:    1  ->  also
+   5:    1  ->  and
+   6:    1  ->  buster
+   7:    1  ->  ends
+   8:    1  ->  films
+   9:    1  ->  had
+  10:    1  ->  medium
+  11:    1  ->  of
+  12:    1  ->  reservations
+  13:    1  ->  right
+  14:    1  ->  six
+  15:    1  ->  that
+  16:    1  ->  the
+     -------
+        17
+
+
+* NOTE: The 'Substitution' words are those reference words
+        for which the recognizer supplied an incorrect word.
+
+
+FALSELY RECOGNIZED               Total                 (15)
+                                 With >=  1 occurrences (15)
+
+   1:    2  ->  a
+   2:    2  ->  thes
+   3:    1  ->  alsas
+   4:    1  ->  alsasls
+   5:    1  ->  available
+   6:    1  ->  californias
+   7:    1  ->  ends
+   8:    1  ->  hus
+   9:    1  ->  moa
+  10:    1  ->  moas
+  11:    1  ->  thea
+  12:    1  ->  theas
+  13:    1  ->  thels
+  14:    1  ->  was
+  15:    1  ->  wasasasasasaslasasasas
+     -------
+        17
+
+
+* NOTE: The 'Falsely Recognized' words are those hypothesis words
+        which the recognizer incorrectly substituted for a reference word.
+

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn.snt.utt

@@ -0,0 +1,85 @@
+===============================================================================
+
+                     SENTENCE LEVEL REPORT FOR THE SYSTEM:
+    Name: /scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn
+
+===============================================================================
+
+
+SPEAKER utt
+id: (utterance_0)
+Scores: (#C #S #D #I) 0 10 3 0
+REF:  JOE KEATON DISAPPROVED OF FILMS AND       BUSTER ALSO HAD  RESERVATIONS ABOUT THE   MEDIUM 
+HYP:  *** ****** *********** A  WAS   AVAILABLE MOA    MOAS THEA ENDS         THEAS THELS THES   
+Eval: D   D      D           S  S     S         S      S    S    S            S     S     S      
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =   76.9%   10   ( 10)
+Deletions             =   23.1%    3   (  3)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =  100.0%   13   ( 13)
+
+Ref. words            =           13   ( 13)
+Hyp. words            =           10   ( 10)
+Aligned words         =           13   ( 13)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_1)
+Scores: (#C #S #D #I) 0 1 3 0
+REF:  SHELL BE ALL RIGHT 
+HYP:  ***** ** *** HUS   
+Eval: D     D  D   S     
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =   25.0%    1   ( 11)
+Deletions             =   75.0%    3   (  6)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =  100.0%    4   ( 17)
+
+Ref. words            =            4   ( 17)
+Hyp. words            =            1   ( 11)
+Aligned words         =            4   ( 17)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_2)
+Scores: (#C #S #D #I) 0 1 0 2
+REF:  ****** ********* SIX  
+HYP:  ASASAS THEASLSAS THES 
+Eval: I      I         S    
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =  100.0%    1   ( 12)
+Deletions             =    0.0%    0   (  6)
+Insertions            =  200.0%    2   (  2)
+
+Errors                =  300.0%    3   ( 20)
+
+Ref. words            =            1   ( 18)
+Hyp. words            =            3   ( 14)
+Aligned words         =            3   ( 20)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_3)
+Scores: (#C #S #D #I) 0 5 0 0
+REF:  ALLS WELL                   THAT        ENDS    WELL  
+HYP:  A    WASASASASASASLASASASAS CALIFORNIAS ALSASLS ALSAS 
+Eval: S    S                      S           S       S     
+
+Correct               =    0.0%    0   (  0)
+Substitutions         =  100.0%    5   ( 17)
+Deletions             =    0.0%    0   (  6)
+Insertions            =    0.0%    0   (  2)
+
+Errors                =  100.0%    5   ( 25)
+
+Ref. words            =            5   ( 23)
+Hyp. words            =            5   ( 19)
+Aligned words         =            5   ( 25)
+
+-------------------------------------------------------------------------------
+

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn.sys

@@ -0,0 +1,18 @@
+
+
+
+                     SYSTEM SUMMARY PERCENTAGES by SPEAKER                      
+
+,--------------------------------------------------------------------------------------------------------------------------------------------------------------------------.
+|/scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn|
+|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|       SPKR         |       # Snt            # Wrd       |       Corr                Sub                Del               Ins                Err              S.Err       |
+|--------------------+------------------------------------+----------------------------------------------------------------------------------------------------------------|
+|       utt          |          4                23       |        0.0               73.9               26.1               8.7              108.7              100.0       |
+|==========================================================================================================================================================================|
+|       Sum/Avg      |          4                23       |        0.0               73.9               26.1               8.7              108.7              100.0       |
+|==========================================================================================================================================================================|
+|        Mean        |        4.0              23.0       |        0.0               73.9               26.1               8.7              108.7              100.0       |
+|        S.D.        |        0.0               0.0       |        0.0                0.0                0.0               0.0                0.0                0.0       |
+|       Median       |        4.0              23.0       |        0.0               73.9               26.1               8.7              108.7              100.0       |
+`--------------------------------------------------------------------------------------------------------------------------------------------------------------------------'

predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_ref.trn

@@ -0,0 +1,4 @@
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_0)
+shell be all right (utterance_1)
+six (utterance_2)
+alls well that ends well (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer156.52.csv

@@ -0,0 +1,5 @@
+label,prediction
+joe keaton disapproved of films and buster also had reservations about the medium,s ofs thes ofs year
+shell be all right,thes thes withs ofs year
+six,thes withsss ofss
+alls well that ends well,s ofs thes withs ofs ofs her withs thess thesss thes thess thesss thes thes

predictions_common_voice_13_en_common_voice_13_en_test_wer156.52_hyp.trn

@@ -0,0 +1,4 @@
+s ofs thes ofs year (utterance_0)
+thes thes withs ofs year (utterance_1)
+thes withsss ofss (utterance_2)
+s ofs thes withs ofs ofs her withs thess thesss thes thess thesss thes thes (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer156.52_ref.trn

@@ -0,0 +1,4 @@
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_0)
+shell be all right (utterance_1)
+six (utterance_2)
+alls well that ends well (utterance_3)

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29.csv

@@ -0,0 +1,27 @@
+label,prediction
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right
+six,six
+alls well that ends well,oswell that ends well
+joe keaton disapproved of films and buster also had reservations about the medium,joel keaton disapproved of films and buster also had reservations about the medium
+shell be all right,j be a right

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn

@@ -0,0 +1,26 @@
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_0)
+j be a right (utterance_1)
+six (utterance_2)
+oswell that ends well (utterance_3)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_4)
+j be a right (utterance_5)
+six (utterance_6)
+oswell that ends well (utterance_7)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_8)
+j be a right (utterance_9)
+six (utterance_10)
+oswell that ends well (utterance_11)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_12)
+j be a right (utterance_13)
+six (utterance_14)
+oswell that ends well (utterance_15)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_16)
+j be a right (utterance_17)
+six (utterance_18)
+oswell that ends well (utterance_19)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_20)
+j be a right (utterance_21)
+six (utterance_22)
+oswell that ends well (utterance_23)
+joel keaton disapproved of films and buster also had reservations about the medium (utterance_24)
+j be a right (utterance_25)

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn.dtl

@@ -0,0 +1,86 @@
+DETAILED OVERALL REPORT FOR THE SYSTEM: /scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn
+
+SENTENCE RECOGNITION PERFORMANCE
+
+ sentences                                          26
+ with errors                             76.9%   (  20)
+
+   with substitutions                    76.9%   (  20)
+   with deletions                        23.1%   (   6)
+   with insertions                        0.0%   (   0)
+
+
+WORD RECOGNITION PERFORMANCE
+
+Percent Total Error       =   21.3%   (  33)
+
+Percent Correct           =   78.7%   ( 122)
+
+Percent Substitution      =   17.4%   (  27)
+Percent Deletions         =    3.9%   (   6)
+Percent Insertions        =    0.0%   (   0)
+Percent Word Accuracy     =   78.7%
+
+
+Ref. words                =           ( 155)
+Hyp. words                =           ( 149)
+Aligned words             =           ( 155)
+
+CONFUSION PAIRS                  Total                 (4)
+                                 With >=  1 occurrences (4)
+
+   1:    7  ->  all ==> a
+   2:    7  ->  joe ==> joel
+   3:    7  ->  shell ==> j
+   4:    6  ->  well ==> oswell
+     -------
+        27
+
+
+
+INSERTIONS                       Total                 (0)
+                                 With >=  1 occurrences (0)
+
+     -------
+         0
+
+
+
+DELETIONS                        Total                 (1)
+                                 With >=  1 occurrences (1)
+
+   1:    6  ->  alls
+     -------
+         6
+
+
+
+SUBSTITUTIONS                    Total                 (4)
+                                 With >=  1 occurrences (4)
+
+   1:    7  ->  all
+   2:    7  ->  joe
+   3:    7  ->  shell
+   4:    6  ->  well
+     -------
+        27
+
+
+* NOTE: The 'Substitution' words are those reference words
+        for which the recognizer supplied an incorrect word.
+
+
+FALSELY RECOGNIZED               Total                 (4)
+                                 With >=  1 occurrences (4)
+
+   1:    7  ->  a
+   2:    7  ->  j
+   3:    7  ->  joel
+   4:    6  ->  oswell
+     -------
+        27
+
+
+* NOTE: The 'Falsely Recognized' words are those hypothesis words
+        which the recognizer incorrectly substituted for a reference word.
+

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn.snt.utt

@@ -0,0 +1,503 @@
+===============================================================================
+
+                     SENTENCE LEVEL REPORT FOR THE SYSTEM:
+    Name: /scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn
+
+===============================================================================
+
+
+SPEAKER utt
+id: (utterance_0)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   ( 12)
+Substitutions         =    7.7%    1   (  1)
+Deletions             =    0.0%    0   (  0)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   (  1)
+
+Ref. words            =           13   ( 13)
+Hyp. words            =           13   ( 13)
+Aligned words         =           13   ( 13)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_1)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   ( 14)
+Substitutions         =   50.0%    2   (  3)
+Deletions             =    0.0%    0   (  0)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   (  3)
+
+Ref. words            =            4   ( 17)
+Hyp. words            =            4   ( 17)
+Aligned words         =            4   ( 17)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_2)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   ( 15)
+Substitutions         =    0.0%    0   (  3)
+Deletions             =    0.0%    0   (  0)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   (  3)
+
+Ref. words            =            1   ( 18)
+Hyp. words            =            1   ( 18)
+Aligned words         =            1   ( 18)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_3)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   ( 18)
+Substitutions         =   20.0%    1   (  4)
+Deletions             =   20.0%    1   (  1)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   (  5)
+
+Ref. words            =            5   ( 23)
+Hyp. words            =            4   ( 22)
+Aligned words         =            5   ( 23)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_4)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   ( 30)
+Substitutions         =    7.7%    1   (  5)
+Deletions             =    0.0%    0   (  1)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   (  6)
+
+Ref. words            =           13   ( 36)
+Hyp. words            =           13   ( 35)
+Aligned words         =           13   ( 36)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_5)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   ( 32)
+Substitutions         =   50.0%    2   (  7)
+Deletions             =    0.0%    0   (  1)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   (  8)
+
+Ref. words            =            4   ( 40)
+Hyp. words            =            4   ( 39)
+Aligned words         =            4   ( 40)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_6)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   ( 33)
+Substitutions         =    0.0%    0   (  7)
+Deletions             =    0.0%    0   (  1)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   (  8)
+
+Ref. words            =            1   ( 41)
+Hyp. words            =            1   ( 40)
+Aligned words         =            1   ( 41)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_7)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   ( 36)
+Substitutions         =   20.0%    1   (  8)
+Deletions             =   20.0%    1   (  2)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   ( 10)
+
+Ref. words            =            5   ( 46)
+Hyp. words            =            4   ( 44)
+Aligned words         =            5   ( 46)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_8)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   ( 48)
+Substitutions         =    7.7%    1   (  9)
+Deletions             =    0.0%    0   (  2)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   ( 11)
+
+Ref. words            =           13   ( 59)
+Hyp. words            =           13   ( 57)
+Aligned words         =           13   ( 59)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_9)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   ( 50)
+Substitutions         =   50.0%    2   ( 11)
+Deletions             =    0.0%    0   (  2)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   ( 13)
+
+Ref. words            =            4   ( 63)
+Hyp. words            =            4   ( 61)
+Aligned words         =            4   ( 63)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_10)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   ( 51)
+Substitutions         =    0.0%    0   ( 11)
+Deletions             =    0.0%    0   (  2)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   ( 13)
+
+Ref. words            =            1   ( 64)
+Hyp. words            =            1   ( 62)
+Aligned words         =            1   ( 64)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_11)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   ( 54)
+Substitutions         =   20.0%    1   ( 12)
+Deletions             =   20.0%    1   (  3)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   ( 15)
+
+Ref. words            =            5   ( 69)
+Hyp. words            =            4   ( 66)
+Aligned words         =            5   ( 69)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_12)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   ( 66)
+Substitutions         =    7.7%    1   ( 13)
+Deletions             =    0.0%    0   (  3)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   ( 16)
+
+Ref. words            =           13   ( 82)
+Hyp. words            =           13   ( 79)
+Aligned words         =           13   ( 82)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_13)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   ( 68)
+Substitutions         =   50.0%    2   ( 15)
+Deletions             =    0.0%    0   (  3)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   ( 18)
+
+Ref. words            =            4   ( 86)
+Hyp. words            =            4   ( 83)
+Aligned words         =            4   ( 86)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_14)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   ( 69)
+Substitutions         =    0.0%    0   ( 15)
+Deletions             =    0.0%    0   (  3)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   ( 18)
+
+Ref. words            =            1   ( 87)
+Hyp. words            =            1   ( 84)
+Aligned words         =            1   ( 87)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_15)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   ( 72)
+Substitutions         =   20.0%    1   ( 16)
+Deletions             =   20.0%    1   (  4)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   ( 20)
+
+Ref. words            =            5   ( 92)
+Hyp. words            =            4   ( 88)
+Aligned words         =            5   ( 92)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_16)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   ( 84)
+Substitutions         =    7.7%    1   ( 17)
+Deletions             =    0.0%    0   (  4)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   ( 21)
+
+Ref. words            =           13   (105)
+Hyp. words            =           13   (101)
+Aligned words         =           13   (105)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_17)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   ( 86)
+Substitutions         =   50.0%    2   ( 19)
+Deletions             =    0.0%    0   (  4)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   ( 23)
+
+Ref. words            =            4   (109)
+Hyp. words            =            4   (105)
+Aligned words         =            4   (109)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_18)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   ( 87)
+Substitutions         =    0.0%    0   ( 19)
+Deletions             =    0.0%    0   (  4)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   ( 23)
+
+Ref. words            =            1   (110)
+Hyp. words            =            1   (106)
+Aligned words         =            1   (110)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_19)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   ( 90)
+Substitutions         =   20.0%    1   ( 20)
+Deletions             =   20.0%    1   (  5)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   ( 25)
+
+Ref. words            =            5   (115)
+Hyp. words            =            4   (110)
+Aligned words         =            5   (115)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_20)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   (102)
+Substitutions         =    7.7%    1   ( 21)
+Deletions             =    0.0%    0   (  5)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   ( 26)
+
+Ref. words            =           13   (128)
+Hyp. words            =           13   (123)
+Aligned words         =           13   (128)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_21)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   (104)
+Substitutions         =   50.0%    2   ( 23)
+Deletions             =    0.0%    0   (  5)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   ( 28)
+
+Ref. words            =            4   (132)
+Hyp. words            =            4   (127)
+Aligned words         =            4   (132)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_22)
+Scores: (#C #S #D #I) 1 0 0 0
+REF:  six 
+HYP:  six 
+Eval:     
+
+Correct               =  100.0%    1   (105)
+Substitutions         =    0.0%    0   ( 23)
+Deletions             =    0.0%    0   (  5)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    0.0%    0   ( 28)
+
+Ref. words            =            1   (133)
+Hyp. words            =            1   (128)
+Aligned words         =            1   (133)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_23)
+Scores: (#C #S #D #I) 3 1 1 0
+REF:  ALLS WELL   that ends well 
+HYP:  **** OSWELL that ends well 
+Eval: D    S                     
+
+Correct               =   60.0%    3   (108)
+Substitutions         =   20.0%    1   ( 24)
+Deletions             =   20.0%    1   (  6)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   40.0%    2   ( 30)
+
+Ref. words            =            5   (138)
+Hyp. words            =            4   (132)
+Aligned words         =            5   (138)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_24)
+Scores: (#C #S #D #I) 12 1 0 0
+REF:  JOE  keaton disapproved of films and buster also had reservations about the medium 
+HYP:  JOEL keaton disapproved of films and buster also had reservations about the medium 
+Eval: S                                                                                  
+
+Correct               =   92.3%   12   (120)
+Substitutions         =    7.7%    1   ( 25)
+Deletions             =    0.0%    0   (  6)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =    7.7%    1   ( 31)
+
+Ref. words            =           13   (151)
+Hyp. words            =           13   (145)
+Aligned words         =           13   (151)
+
+-------------------------------------------------------------------------------
+
+id: (utterance_25)
+Scores: (#C #S #D #I) 2 2 0 0
+REF:  SHELL be ALL right 
+HYP:  J     be A   right 
+Eval: S        S         
+
+Correct               =   50.0%    2   (122)
+Substitutions         =   50.0%    2   ( 27)
+Deletions             =    0.0%    0   (  6)
+Insertions            =    0.0%    0   (  0)
+
+Errors                =   50.0%    2   ( 33)
+
+Ref. words            =            4   (155)
+Hyp. words            =            4   (149)
+Aligned words         =            4   (155)
+
+-------------------------------------------------------------------------------
+

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn.sys

@@ -0,0 +1,18 @@
+
+
+
+                     SYSTEM SUMMARY PERCENTAGES by SPEAKER                      
+
+,-------------------------------------------------------------------------------------------------------------------------------------------------------------------------.
+|/scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_hyp.trn|
+|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|       SPKR         |      # Snt             # Wrd       |       Corr               Sub                Del                Ins               Err              S.Err       |
+|--------------------+------------------------------------+---------------------------------------------------------------------------------------------------------------|
+|       utt          |        26                155       |       78.7              17.4                3.9                0.0              21.3               76.9       |
+|=========================================================================================================================================================================|
+|       Sum/Avg      |        26                155       |       78.7              17.4                3.9                0.0              21.3               76.9       |
+|=========================================================================================================================================================================|
+|        Mean        |      26.0              155.0       |       78.7              17.4                3.9                0.0              21.3               76.9       |
+|        S.D.        |       0.0                0.0       |        0.0               0.0                0.0                0.0               0.0                0.0       |
+|       Median       |      26.0              155.0       |       78.7              17.4                3.9                0.0              21.3               76.9       |
+`-------------------------------------------------------------------------------------------------------------------------------------------------------------------------'

predictions_common_voice_13_en_common_voice_13_en_test_wer21.29_ref.trn

@@ -0,0 +1,26 @@
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_0)
+shell be all right (utterance_1)
+six (utterance_2)
+alls well that ends well (utterance_3)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_4)
+shell be all right (utterance_5)
+six (utterance_6)
+alls well that ends well (utterance_7)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_8)
+shell be all right (utterance_9)
+six (utterance_10)
+alls well that ends well (utterance_11)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_12)
+shell be all right (utterance_13)
+six (utterance_14)
+alls well that ends well (utterance_15)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_16)
+shell be all right (utterance_17)
+six (utterance_18)
+alls well that ends well (utterance_19)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_20)
+shell be all right (utterance_21)
+six (utterance_22)
+alls well that ends well (utterance_23)
+joe keaton disapproved of films and buster also had reservations about the medium (utterance_24)
+shell be all right (utterance_25)

predictions_common_voice_13_en_common_voice_13_en_test_wer26.31_hyp.trn.snt.utt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a2e626069436b4700a4c81206d42dd9fac798290a90be354f999f37e9be969
+size 11492598

predictions_common_voice_13_en_common_voice_13_en_test_wer26.31_hyp.trn.sys

@@ -0,0 +1,18 @@
+
+
+
+                     SYSTEM SUMMARY PERCENTAGES by SPEAKER                      
+
+,-------------------------------------------------------------------------------------------------------------------------------------------------------------------------.
+|/scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer26.31_hyp.trn|
+|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|      SPKR         |       # Snt               # Wrd        |      Corr                Sub               Del               Ins               Err             S.Err       |
+|-------------------+----------------------------------------+------------------------------------------------------------------------------------------------------------|
+|      utt          |      16384               144172        |      77.2               17.8               5.1               3.5              26.3              69.5       |
+|=========================================================================================================================================================================|
+|      Sum/Avg      |      16384               144172        |      77.2               17.8               5.1               3.5              26.3              69.5       |
+|=========================================================================================================================================================================|
+|       Mean        |     16384.0             144172.0       |      77.2               17.8               5.1               3.5              26.3              69.5       |
+|       S.D.        |        0.0                 0.0         |       0.0                0.0               0.0               0.0               0.0               0.0       |
+|      Median       |     16384.0             144172.0       |      77.2               17.8               5.1               3.5              26.3              69.5       |
+`-------------------------------------------------------------------------------------------------------------------------------------------------------------------------'

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610498329fd4c2cbe33c90d47b3294863967e0d466b0680feb038c21e1d4e281
+size 5816