Model save

.ipynb_checkpoints/run-checkpoint.sh

@@ -1,7 +1,7 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="common_voice" \
 	--model_name_or_path="hf-test/xls-r-dummy" \
-	--dataset_config_name="ab" \
+	--dataset_config_name="hi" \
 	--output_dir="./" \
 	--overwrite_output_dir \
 	--num_train_epochs="2" \

README.md

@@ -1,63 +0,0 @@
----
-language:
-- ab
-tags:
-- automatic-speech-recognition
-- common_voice
-- generated_from_trainer
-datasets:
-- common_voice
-model-index:
-- name: ''
-  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. -->
-
-# 
-
-This model is a fine-tuned version of [hf-test/xls-r-dummy](https://huggingface.co/hf-test/xls-r-dummy) on the COMMON_VOICE - AB dataset.
-It achieves the following results on the evaluation set:
-- Loss: 133.5167
-- Wer: 18.9286
-
-## 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: 0.0003
-- train_batch_size: 16
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 2.0
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.17.0.dev0
-- Pytorch 1.10.2+cu102
-- Datasets 1.18.2.dev0
-- Tokenizers 0.11.0

added_tokens.json

@@ -1 +1 @@
-{"<s>": 40, "</s>": 41}
+{"<s>": 73, "</s>": 74}

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 2.0,
-    "eval_loss": 133.51673889160156,
-    "eval_runtime": 0.3897,
-    "eval_samples": 9,
-    "eval_samples_per_second": 23.093,
-    "eval_steps_per_second": 5.132,
-    "eval_wer": 18.928571428571427,
-    "train_loss": 147.0714569091797,
-    "train_runtime": 2.5065,
-    "train_samples": 22,
-    "train_samples_per_second": 17.554,
-    "train_steps_per_second": 0.798
-}

config.json

@@ -65,7 +65,7 @@
   "num_hidden_layers": 4,
   "num_negatives": 10,
   "output_hidden_size": 16,
-  "pad_token_id": 39,
+  "pad_token_id": 72,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -91,6 +91,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.17.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 42,
+  "vocab_size": 75,
   "xvector_output_dim": 512
 }

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 2.0,
-    "eval_loss": 133.51673889160156,
-    "eval_runtime": 0.3897,
-    "eval_samples": 9,
-    "eval_samples_per_second": 23.093,
-    "eval_steps_per_second": 5.132,
-    "eval_wer": 18.928571428571427
-}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac89a4d5306b1b0af49e557b2cf55ff2eae830d8e96f3da9876d516bfe96bf71
-size 143142
+oid sha256:13da8c174ad4ca85332500aa28ebddb71c1a57676867c30cd905a77f61bd43a9
+size 145382

run.sh

@@ -1,7 +1,7 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="common_voice" \
 	--model_name_or_path="hf-test/xls-r-dummy" \
-	--dataset_config_name="ab" \
+	--dataset_config_name="hi" \
 	--output_dir="./" \
 	--overwrite_output_dir \
 	--num_train_epochs="2" \

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 2.0,
-    "train_loss": 147.0714569091797,
-    "train_runtime": 2.5065,
-    "train_samples": 22,
-    "train_samples_per_second": 17.554,
-    "train_steps_per_second": 0.798
-}

trainer_state.json

@@ -1,25 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "global_step": 2,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 2.0,
-      "step": 2,
-      "total_flos": 1024005998592.0,
-      "train_loss": 147.0714569091797,
-      "train_runtime": 2.5065,
-      "train_samples_per_second": 17.554,
-      "train_steps_per_second": 0.798
-    }
-  ],
-  "max_steps": 2,
-  "num_train_epochs": 2,
-  "total_flos": 1024005998592.0,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abf70ee833af8d8c22a2c8a2cbecfd532a51e2b5d92efc5025a369bcd756a19
+oid sha256:7e7c49f436f35bafb5f2bb54a872e96c104c766a78f634853f8b33dfc5ba4646
 size 2991

vocab.json

@@ -1 +1 @@
-{"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "к": 10, "л": 11, "м": 12, "н": 13, "о": 14, "п": 15, "р": 16, "с": 17, "т": 18, "у": 19, "ф": 20, "х": 21, "ц": 22, "ш": 23, "ы": 24, "ь": 25, "қ": 26, "ҟ": 27, "ҩ": 28, "ҭ": 29, "ҳ": 30, "ҵ": 31, "ҽ": 32, "ҿ": 33, "ә": 34, "ӡ": 35, "ӷ": 36, "ԥ": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
+{"a": 1, "e": 2, "f": 3, "i": 4, "l": 5, "m": 6, "p": 7, "r": 8, "u": 9, "w": 10, "ँ": 11, "ं": 12, "ः": 13, "अ": 14, "आ": 15, "इ": 16, "ई": 17, "उ": 18, "ऊ": 19, "ए": 20, "ऐ": 21, "ऑ": 22, "ओ": 23, "औ": 24, "क": 25, "ख": 26, "ग": 27, "घ": 28, "च": 29, "छ": 30, "ज": 31, "झ": 32, "ट": 33, "ठ": 34, "ड": 35, "ढ": 36, "ण": 37, "त": 38, "थ": 39, "द": 40, "ध": 41, "न": 42, "प": 43, "फ": 44, "ब": 45, "भ": 46, "म": 47, "य": 48, "र": 49, "ल": 50, "व": 51, "श": 52, "ष": 53, "स": 54, "ह": 55, "़": 56, "ा": 57, "ि": 58, "ी": 59, "ु": 60, "ू": 61, "ृ": 62, "े": 63, "ै": 64, "ॉ": 65, "ो": 66, "ौ": 67, "्": 68, "ड़": 69, "।": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}