Upload folder using huggingface_hub

.gitattributes

@@ -2,34 +2,28 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+transcriptions_cv7_test.json filter=lfs diff=lfs merge=lfs -text
+transcriptions_cv7_validation.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,17 @@
+---
+language:
+- it
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- it
+datasets:
+- mozilla-foundation/common_voice_7_0
+---
+# exp_w2v2t_it_vp-100k_s449
+
+Fine-tuned [facebook/wav2vec2-large-100k-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-100k-voxpopuli) for speech recognition using the train split of [Common Voice 7.0 (it)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.
+    

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "'", "-", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u00e0", "\u00e1", "\u00e8", "\u00e9", "\u00ec", "\u00ed", "\u00f2", "\u00f3", "\u00f9", "\u00fa", "\u010d", "\u014d", "\u0161"], "is_bpe": false}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-100k-voxpopuli",
+  "activation_dropout": 0.05,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "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": "sum",
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 0,
+  "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": "4.15.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 46,
+  "xvector_output_dim": 512
+}

language_model/2gram_Fr_Ref.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8473244614177ba579a429eee07aa150132b9a1b2209025dbe3ffee6f1fe003d
+size 12867

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 +1,230 @@
+</s>
+<s>
+absence
+amour
+anglage
+argile
+baie
+bain
+balade
+bambou
+bante
+baptême
+barrage
+basket
+bastiore
+bente
+beuil
+bille
+boeufs
+bonfage
+bonheur
+brume
+brumidurence
+brète
+bucurelle
+buson
+béret
+cage
+canchoir
+caravelle
+carotte
+carré
+case
+casier
+catastrophe
+cellier
+cerceau
+chaleur
+chambre
+champagne
+chanson
+chemisier
+choix
+cieux
+commande
+compagne
+compteur
+conjeau
+consigne
+couette
+couleur
+coïncidence
+crâne
+crêpe
+crête
+cuisinier
+cutice
+daveau
+demande
+dieux
+digacelle
+dille
+diège
+donte
+duie
+débarquement
+délice
+déménagement
+département
+désir
+escroc
+excitation
+faisceau
+fari
+façade
+faïence
+ferraille
+fident
+figure
+fille
+filou
+firoie
+flunobirence
+foire
+fossile
+fossé
+frère
+fureur
+garçonnet
+genévrier
+gigot
+goix
+gouache
+grasention
+grève
+guidon
+haie
+hogeur
+hupeur
+héteur
+hôtel
+indiscrétion
+initiation
+instruments
+intelligence
+jardinet
+jauf
+jeans
+jeul
+jeur
+joie
+jol
+jorcantion
+joue
+juin
+juit
+lagul
+lait
+lamon
+lesoie
+lieux
+liège
+loif
+lumèce
+légende
+malice
+manivelle
+matou
+menuisier
+meuil
+milvenet
+mirabelle
+mise
+montage
+mouette
+moulinet
+muson
+métal
+nage
+nardé
+navet
+nille
+ninoie
+noeuds
+noix
+nombre
+notice
+nuit
+oeufs
+opposition
+orchestre
+ouest
+parade
+paroce
+passé
+patience
+pause
+pente
+perné
+phème
+pinson
+pireau
+piège
+pléfantion
+poids
+poire
+production
+précision
+puli
+pune
+pâté
+quille
+race
+raie
+raplème
+rari
+ratase
+reconnaissance
+regret
+reptile
+reuil
+reux
+rille
+rof
+rombage
+ronjeau
+rose
+rosier
+ruit
+réclamation
+régal
+saison
+sauvage
+secret
+septième
+sidomelle
+siège
+sorpile
+stade
+stand
+style
+suf
+tanjeau
+tenaille
+tente
+terfonet
+terreau
+test
+timbre
+tiveau
+tiège
+toir
+toit
+tondé
+tradition
+trufondulence
+trèbe
+trème
+tuit
+tumpunet
+turlème
+valet
+valeur
+vente
+voix
+voleur
+zeux
+écaille
+écho
+élève

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7281f836a6c24a0cb01dcd6abcaccc1d05af48807a5138b3f39c235904e0d7f
+size 1262112241

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": "|"
+}

transcriptions_cv7_test.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7ccd1835ec95183cc10c41dddf4532f3700c79d1d9979197242a697c24ce54
+size 78764122

transcriptions_cv7_validation.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ec28e9aa51878172c99ac03e1d68611f1a37bc6acd12fa96b22a2f474e1a3c
+size 78184898

vocab.json

@@ -0,0 +1,48 @@
+{
+  "'": 5,
+  "-": 6,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "a": 7,
+  "b": 8,
+  "c": 9,
+  "d": 10,
+  "e": 11,
+  "f": 12,
+  "g": 13,
+  "h": 14,
+  "i": 15,
+  "j": 16,
+  "k": 17,
+  "l": 18,
+  "m": 19,
+  "n": 20,
+  "o": 21,
+  "p": 22,
+  "q": 23,
+  "r": 24,
+  "s": 25,
+  "t": 26,
+  "u": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "z": 32,
+  "|": 4,
+  "à": 33,
+  "á": 34,
+  "è": 35,
+  "é": 36,
+  "ì": 37,
+  "í": 38,
+  "ò": 39,
+  "ó": 40,
+  "ù": 41,
+  "ú": 42,
+  "č": 43,
+  "ō": 44,
+  "š": 45
+}