Training in progress, step 5

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 47, "</s>": 48}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 46,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 49,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b1c01e49bb45b520bac2e8efbe362c098c3e895beeea286ed670b719bf4e2c
+size 1262124593

requierments.txt

@@ -2,4 +2,5 @@ git+https://github.com/huggingface/transformers.git#egg=transformers[torch-speec
 git+https://github.com/huggingface/datasets.git#egg=datasets[streaming]
 torchaudio
 librosa
-jiwer
+jiwer
+bitsandbytes-cuda113

run.sh

@@ -1,14 +1,14 @@
 #!/bin/sh
 
 export CUDA_VISIBLE_DEVICES=1,2
-python run_speech_recognition_ctc.py \
+python run_speech_recognition_ctc_bnb.py \
        --dataset_name="mozilla-foundation/common_voice_7_0" \
        --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
        --dataset_config_name="et" \
        --output_dir="./" \
        --overwrite_output_dir \
        --max_steps="10" \
-       --per_device_train_batch_size="2" \
+       --per_device_train_batch_size="4" \
        --learning_rate="3e-4" \
        --save_total_limit="1" \
        --evaluation_strategy="steps" \

special_tokens_map.json

@@ -0,0 +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}]}

tokenizer_config.json

@@ -0,0 +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"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32e1488960b88d8baf2fe427aa7735404817fc7cd41b4665535416bcacf7216
+size 2991

vocab.json

@@ -0,0 +1 @@
+{"!": 1, "\"": 2, "'": 3, ",": 4, "-": 5, ".": 6, ";": 7, "?": 8, "a": 9, "b": 10, "c": 11, "d": 12, "e": 13, "f": 14, "g": 15, "h": 16, "i": 17, "j": 18, "k": 19, "l": 20, "m": 21, "n": 22, "o": 23, "p": 24, "q": 25, "r": 26, "s": 27, "t": 28, "u": 29, "v": 30, "w": 31, "x": 32, "y": 33, "z": 34, "ä": 35, "õ": 36, "ö": 37, "ü": 38, "š": 39, "ž": 40, "̇": 41, "’": 42, "“": 43, "„": 44, "|": 0, "[UNK]": 45, "[PAD]": 46}