Model save

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_16_0
+model-index:
+- name: wav2vec2-common_voice-af-demo
+  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. -->
+
+# wav2vec2-common_voice-af-demo
+
+This model was trained from scratch on the common_voice_16_0 dataset.
+
+## 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: 15.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 32,
+  "<s>": 31
+}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "/home/yoach/tmp/wav2vec_seamless",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2ConformerForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_depthwise_kernel_size": 31,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    160
+  ],
+  "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,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "non_causal_depth_wise_conv": false,
+  "num_adapter_layers": 0,
+  "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": 30,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "skip_encoder_layer_norm": true,
+  "skip_feature_encoder": true,
+  "skip_pos_conv_embed": true,
+  "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": "4.37.0.dev0",
+  "use_adapter_with_attention": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2024-01-01T15:21:31,ec6bfdc1-9b67-4d1a-a0fa-b70b3193b238,codecarbon,88.12444925308228,0.003465083577686595,0.008161127492751757,France,FRA,île-de-france,N,,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58144bc40ec982cf107933af97be6214d052a81a670e784f3c578b1227a069f
+size 2322213876

preprocessor_config.json

@@ -0,0 +1,112 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 80,
+  "language_code": [
+    "__afr__",
+    "__amh__",
+    "__arb__",
+    "__ary__",
+    "__arz__",
+    "__asm__",
+    "__azj__",
+    "__bel__",
+    "__ben__",
+    "__bos__",
+    "__bul__",
+    "__cat__",
+    "__ceb__",
+    "__ces__",
+    "__ckb__",
+    "__cmn__",
+    "__cmn_Hant__",
+    "__cym__",
+    "__dan__",
+    "__deu__",
+    "__ell__",
+    "__eng__",
+    "__est__",
+    "__eus__",
+    "__fin__",
+    "__fra__",
+    "__fuv__",
+    "__gaz__",
+    "__gle__",
+    "__glg__",
+    "__guj__",
+    "__heb__",
+    "__hin__",
+    "__hrv__",
+    "__hun__",
+    "__hye__",
+    "__ibo__",
+    "__ind__",
+    "__isl__",
+    "__ita__",
+    "__jav__",
+    "__jpn__",
+    "__kan__",
+    "__kat__",
+    "__kaz__",
+    "__khk__",
+    "__khm__",
+    "__kir__",
+    "__kor__",
+    "__lao__",
+    "__lit__",
+    "__lug__",
+    "__luo__",
+    "__lvs__",
+    "__mai__",
+    "__mal__",
+    "__mar__",
+    "__mkd__",
+    "__mlt__",
+    "__mni__",
+    "__mya__",
+    "__nld__",
+    "__nno__",
+    "__nob__",
+    "__npi__",
+    "__nya__",
+    "__ory__",
+    "__pan__",
+    "__pbt__",
+    "__pes__",
+    "__pol__",
+    "__por__",
+    "__ron__",
+    "__rus__",
+    "__sat__",
+    "__slk__",
+    "__slv__",
+    "__sna__",
+    "__snd__",
+    "__som__",
+    "__spa__",
+    "__srp__",
+    "__swe__",
+    "__swh__",
+    "__tam__",
+    "__tel__",
+    "__tgk__",
+    "__tgl__",
+    "__tha__",
+    "__tur__",
+    "__ukr__",
+    "__urd__",
+    "__uzn__",
+    "__vie__",
+    "__yor__",
+    "__yue__",
+    "__zlm__",
+    "__zul__"
+  ],
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

runs/Dec22_13-04-34_vorace/events.out.tfevents.1703250345.vorace.2962469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b54ecfe665464697863e38d5a4dbd662ba3acea6513622942b42bd98092ccc
+size 6167

runs/Jan01_15-19-35_vorace/events.out.tfevents.1704122401.vorace.38190.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261d27b5a86246fb57adb54c7647beb4d419130267ee74bba0c81053e54a4e13
+size 6515

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": {
+    "29": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "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": "Wav2Vec2Processor",
+  "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:effa08dffb61eb2cfbc9b89b7595afa0b908795b860765d7460c286f3df242f1
+size 4728

vocab.json

@@ -0,0 +1,33 @@
+{
+  "[PAD]": 30,
+  "[UNK]": 29,
+  "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,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "w": 22,
+  "y": 23,
+  "|": 0,
+  "á": 24,
+  "ê": 25,
+  "ë": 26,
+  "ï": 27,
+  "’": 28
+}