updating

README.md

@@ -1,64 +0,0 @@
----
-language:
-- sv-SE
-license: cc0-1.0
-tags:
-- automatic-speech-recognition
-- mozilla-foundation/common_voice_7_0
-- generated_from_trainer
-datasets:
-- common_voice
-model-index:
-- name: xls-npsc-oh
-  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. -->
-
-# xls-npsc-oh
-
-This model is a fine-tuned version of [KBLab/wav2vec2-large-voxrex](https://huggingface.co/KBLab/wav2vec2-large-voxrex) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2314
-- Wer: 0.64
-
-## 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: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 5.0
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.16.0.dev0
-- Pytorch 1.10.1+cu102
-- Datasets 1.18.1.dev0
-- Tokenizers 0.11.0

added_tokens.json

@@ -1 +1 @@
-{"<s>": 37, "</s>": 38}
+{"<s>": 42, "</s>": 43}

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 5.0,
-    "eval_loss": 0.23142604529857635,
-    "eval_runtime": 3.4384,
-    "eval_samples": 100,
-    "eval_samples_per_second": 29.083,
-    "eval_steps_per_second": 1.163,
-    "eval_wer": 0.64,
-    "train_loss": 3.968093375272529,
-    "train_runtime": 1702.164,
-    "train_samples": 11030,
-    "train_samples_per_second": 32.4,
-    "train_steps_per_second": 0.253
-}

config.json

@@ -6,7 +6,7 @@
   "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForCTC"
+    "Wav2Vec2ForPreTraining"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -84,7 +84,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 36,
+  "pad_token_id": 41,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -107,9 +107,8 @@
     1,
     1
   ],
-  "torch_dtype": "float32",
   "transformers_version": "4.16.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 39,
+  "vocab_size": 44,
   "xvector_output_dim": 512
 }

run.sh

@@ -1,12 +1,12 @@
+#	--dataset_config_name="sv-SE" \
+#	--text_column_name="sentence" \
 #	--dataset_name="NbAiLab/NPSC" \
-#	--dataset_config_name="48K_mp3" \
-#	--text_column_name="text" \
 	
 
 python run_speech_recognition_ctc_bnb.py \
-	--dataset_name="mozilla-foundation/common_voice_7_0" \
-	--dataset_config_name="sv-SE" \
-	--text_column_name="sentence" \
+        --dataset_name="NbAiLab/NPSC" \
+        --dataset_config_name="48K_mp3" \
+        --text_column_name="text" \
 	--model_name_or_path="KBLab/wav2vec2-large-voxrex" \
         --output_dir="./" \
         --overwrite_output_dir \

run_speech_recognition_ctc_bnb.py

@@ -422,8 +422,8 @@ def main():
             split=data_args.train_split_name,
             use_auth_token=data_args.use_auth_token,
         )
-        #raw_datasets["train"] = raw_datasets["train"].filter(preprocess_dataset)
-        #raw_datasets["train"] = raw_datasets["train"].map(map_dataset)
+        raw_datasets["train"] = raw_datasets["train"].filter(preprocess_dataset)
+        raw_datasets["train"] = raw_datasets["train"].map(map_dataset)
 
         if data_args.audio_column_name not in raw_datasets["train"].column_names:
             raise ValueError(
@@ -449,8 +449,8 @@ def main():
             split=data_args.eval_split_name,
             use_auth_token=data_args.use_auth_token,
         )
-        #raw_datasets["eval"] = raw_datasets["eval"].filter(preprocess_dataset)
-        #raw_datasets["eval"] = raw_datasets["eval"].map(map_dataset)
+        raw_datasets["eval"] = raw_datasets["eval"].filter(preprocess_dataset)
+        raw_datasets["eval"] = raw_datasets["eval"].map(map_dataset)
 
         if data_args.max_eval_samples is not None:
             raw_datasets["eval"] = raw_datasets["eval"].select(range(data_args.max_eval_samples))

training_args.bin → runs/Jan27_08-47-37_job-05b2a883-27c6-492e-87b7-30be04252f5c/1643276165.073657/events.out.tfevents.1643276165.job-05b2a883-27c6-492e-87b7-30be04252f5c.3432238.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc71a16af87450f4d2115747ca06fead78d5a9411edbbc77d2195e8cb4ba464
-size 2991
+oid sha256:4c7370a4ed97e246ce9878c734aa0d8443817e16415780f6d8d23dd4d8a6eacb
+size 4768

pytorch_model.bin → runs/Jan27_08-47-37_job-05b2a883-27c6-492e-87b7-30be04252f5c/events.out.tfevents.1643276165.job-05b2a883-27c6-492e-87b7-30be04252f5c.3432238.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205744125a0f7786674fb1a8ba8fa2a297566d91e7a574412df0d88696bec7e9
-size 1262083569
+oid sha256:07042bc1c8b17ec9a02be9d0d35a632dc1e39f8e340770dc86e0ff076a317419
+size 4916

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 5.0,
-    "train_loss": 3.968093375272529,
-    "train_runtime": 1702.164,
-    "train_samples": 11030,
-    "train_samples_per_second": 32.4,
-    "train_steps_per_second": 0.253
-}

trainer_state.json

@@ -1,25 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 4.9971014492753625,
-  "global_step": 430,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 5.0,
-      "step": 430,
-      "total_flos": 5.144546715838387e+18,
-      "train_loss": 3.968093375272529,
-      "train_runtime": 1702.164,
-      "train_samples_per_second": 32.4,
-      "train_steps_per_second": 0.253
-    }
-  ],
-  "max_steps": 430,
-  "num_train_epochs": 5,
-  "total_flos": 5.144546715838387e+18,
-  "trial_name": null,
-  "trial_params": null
-}

vocab.json

@@ -1 +1 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "ä": 27, "å": 28, "é": 29, "ô": 30, "ö": 31, "ü": 32, "“": 33, "”": 34, "|": 0, "[UNK]": 35, "[PAD]": 36}
+{"\\": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, " ": 28, "à": 29, "ä": 30, "å": 31, "æ": 32, "ç": 33, "è": 34, "ò": 35, "ô": 36, "ö": 37, "ø": 38, "ü": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}