Upload folder using huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- generated_from_trainer
+datasets:
+- audiofolder
+metrics:
+- wer
+model-index:
+- name: wav2vec2-base-self-331-colab
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: audiofolder
+      type: audiofolder
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.15007215007215008
+---
+
+<!-- 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. -->
+
+# wav2vec2-base-self-331-colab
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the audiofolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3282
+- Wer: 0.1501
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 300
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 2.3444        | 30.77  | 200  | 2.1940          | 0.9841 |
+| 1.972         | 61.54  | 400  | 1.4582          | 0.8167 |
+| 1.3875        | 92.31  | 600  | 0.8476          | 0.5902 |
+| 0.9092        | 123.08 | 800  | 0.5445          | 0.3636 |
+| 0.6382        | 153.85 | 1000 | 0.4129          | 0.2641 |
+| 0.5789        | 184.62 | 1200 | 0.3497          | 0.1876 |
+| 0.4632        | 215.38 | 1400 | 0.3478          | 0.1616 |
+| 0.4474        | 246.15 | 1600 | 0.3394          | 0.1486 |
+| 0.429         | 276.92 | 1800 | 0.3282          | 0.1501 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 29,
+  "<s>": 28
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "a", "b", "c", "d", "e", "f", "g", "h", "i", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 27,
+  "proj_codevector_dim": 256,
+  "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": "4.38.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bab2b9cbbbc0129a09e4ea49d8fc3054d7d9469cad97732e56584b41edb7db
+size 47141

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/unigrams.txt

@@ -0,0 +1,152 @@
+</s>
+<s>
+a
+after
+air
+alive
+altimeter
+altitude
+and
+anti
+approach
+area
+arm
+around
+auto
+autobrake
+autothrottle
+bark
+before
+bleed
+brake
+brakes
+c
+cabin
+center
+central
+check
+checked
+checklist
+clear
+climb
+collection
+collision
+combine
+complete
+continuous
+control
+de
+descent
+doors
+down
+eight
+emergency
+engine
+equipment
+exist
+exit
+exterior
+external
+f
+feet
+fifteen
+five
+flap
+flaps
+flight
+four
+frequency
+fuel
+full
+gear
+generator
+generators
+give
+glideslope
+go
+green
+ground
+heading
+heat
+hundred
+hydraulic
+i
+ice
+initial
+instrument
+instruments
+isolation
+kilograms
+landing
+left
+level
+lever
+levers
+light
+lights
+localiser
+m
+mode
+model
+nav
+navy
+of
+off
+ok
+on
+one
+open
+p
+packets
+packs
+parking
+parks
+passenger
+pilot
+position
+positive
+preflight
+probe
+pump
+pumps
+r
+rate
+recall
+removed
+right
+roger
+run
+runway
+s
+secure
+selector
+selectors
+set
+shutdown
+signs
+sit
+six
+speed
+start
+switch
+switches
+take
+takeoff
+taking
+tax
+taxi
+thirty
+thousand
+three
+thrust
+trust
+turn
+two
+u
+up
+value
+valve
+wave
+waves
+window
+zero

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fd7260b214995348a399aaf861090b5240be57c8cbf4c6ce1e638b543f4fcf
+size 377611120

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Mar31_06-23-37_ae4be65433ef/events.out.tfevents.1711866264.ae4be65433ef.291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74f491d58cda0b80a36ce8d5c34da8324e67b1d741d61c9478d5e8d47f34a0f
+size 6393

runs/Mar31_06-55-38_ae4be65433ef/events.out.tfevents.1711868160.ae4be65433ef.291.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6373e24f03ef730c5f9c3a78440ddcb742ab0516d38ba5a8e97706e4da2b369
+size 8009

runs/Mar31_08-54-59_ae4be65433ef/events.out.tfevents.1711875323.ae4be65433ef.291.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a76192d7ee93c6811d0c4443c2ea4c23e5fec521a65e7b3403c9d405f40ae9
+size 11183

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "26": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a250123a5e6dedd071ab6ce3622f32ac8a83e63979ae66a38cae8d7cc536ba27
+size 4920

vocab.json

@@ -0,0 +1,30 @@
+{
+  "[PAD]": 27,
+  "[UNK]": 26,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "k": 10,
+  "l": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "p": 15,
+  "q": 16,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "w": 22,
+  "x": 23,
+  "y": 24,
+  "z": 25,
+  "|": 0
+}