Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,27 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
+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

README.md

@@ -0,0 +1,148 @@
+---
+language:
+- it
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- hf-asr-leaderboard
+- it
+- mozilla-foundation/common_voice_8_0
+- robust-speech-event
+datasets:
+- mozilla-foundation/common_voice_8_0
+model-index:
+- name: XLS-R Wav2Vec2 Italian by Jonatas Grosman
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 8
+      type: mozilla-foundation/common_voice_8_0
+      args: it
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 9.04
+    - name: Test CER
+      type: cer
+      value: 2.2
+    - name: Test WER (+LM)
+      type: wer
+      value: 6.75
+    - name: Test CER (+LM)
+      type: cer
+      value: 1.76
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Robust Speech Event - Dev Data
+      type: speech-recognition-community-v2/dev_data
+      args: it
+    metrics:
+    - name: Dev WER
+      type: wer
+      value: 23.38
+    - name: Dev CER
+      type: cer
+      value: 9.41
+    - name: Dev WER (+LM)
+      type: wer
+      value: 15.84
+    - name: Dev CER (+LM)
+      type: cer
+      value: 8.93
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Robust Speech Event - Test Data
+      type: speech-recognition-community-v2/eval_data
+      args: it
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 18.34
+---
+
+# Fine-tuned XLS-R 1B model for speech recognition in Italian
+
+Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Italian using the train and validation splits of [Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0), [Multilingual TEDx](http://www.openslr.org/100), [Multilingual LibriSpeech](https://www.openslr.org/94/), and [Voxpopuli](https://github.com/facebookresearch/voxpopuli).
+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, and thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
+
+## Usage
+
+Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
+
+```python
+from huggingsound import SpeechRecognitionModel
+
+model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-xls-r-1b-italian")
+audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
+
+transcriptions = model.transcribe(audio_paths)
+```
+
+Writing your own inference script:
+
+```python
+import torch
+import librosa
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+LANG_ID = "it"
+MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-italian"
+SAMPLES = 10
+
+test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
+
+processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
+model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    batch["sentence"] = batch["sentence"].upper()
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+with torch.no_grad():
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+predicted_sentences = processor.batch_decode(predicted_ids)
+```
+
+## Evaluation Commands
+
+1. To evaluate on `mozilla-foundation/common_voice_8_0` with split `test`
+
+```bash
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset mozilla-foundation/common_voice_8_0 --config it --split test
+```
+
+2. To evaluate on `speech-recognition-community-v2/dev_data`
+
+```bash
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset speech-recognition-community-v2/dev_data --config it --split validation --chunk_length_s 5.0 --stride_length_s 1.0
+```
+
+## Citation
+If you want to cite this model you can use this:
+
+```bibtex
+@misc{grosman2021xlsr-1b-italian,
+  title={Fine-tuned {XLS-R} 1{B} model for speech recognition in {I}talian},
+  author={Grosman, Jonatas},
+  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-italian}},
+  year={2022}
+}
+```

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"], "is_bpe": false}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-1b",
+  "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": 1024,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "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": 43,
+  "xvector_output_dim": 512
+}

eval.py

@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+from datasets import load_dataset, load_metric, Audio, Dataset
+from transformers import pipeline, AutoFeatureExtractor, AutoTokenizer, AutoConfig, AutoModelForCTC, Wav2Vec2Processor, Wav2Vec2ProcessorWithLM
+import re
+import torch
+import argparse
+from typing import Dict
+
+def log_results(result: Dataset, args: Dict[str, str]):
+    """ DO NOT CHANGE. This function computes and logs the result metrics. """
+
+    log_outputs = args.log_outputs
+    dataset_id = "_".join(args.dataset.split("/") + [args.config, args.split])
+
+    # load metric
+    wer = load_metric("wer")
+    cer = load_metric("cer")
+
+    # compute metrics
+    wer_result = wer.compute(references=result["target"], predictions=result["prediction"])
+    cer_result = cer.compute(references=result["target"], predictions=result["prediction"])
+
+    # print & log results
+    result_str = (
+        f"WER: {wer_result}\n"
+        f"CER: {cer_result}"
+    )
+    print(result_str)
+
+    with open(f"{dataset_id}_eval_results.txt", "w") as f:
+        f.write(result_str)
+
+    # log all results in text file. Possibly interesting for analysis
+    if log_outputs is not None:
+        pred_file = f"log_{dataset_id}_predictions.txt"
+        target_file = f"log_{dataset_id}_targets.txt"
+
+        with open(pred_file, "w") as p, open(target_file, "w") as t:
+
+            # mapping function to write output
+            def write_to_file(batch, i):
+                p.write(f"{i}" + "\n")
+                p.write(batch["prediction"] + "\n")
+                t.write(f"{i}" + "\n")
+                t.write(batch["target"] + "\n")
+
+            result.map(write_to_file, with_indices=True)
+
+
+def normalize_text(text: str, invalid_chars_regex: str, to_lower: bool) -> str:
+    """ DO ADAPT FOR YOUR USE CASE. this function normalizes the target text. """
+
+    text = text.lower() if to_lower else text.upper()
+
+    text = re.sub(invalid_chars_regex, " ", text)
+
+    text = re.sub("\s+", " ", text).strip()
+
+    return text
+
+
+def main(args):
+    # load dataset
+    dataset = load_dataset(args.dataset, args.config, split=args.split, use_auth_token=True)
+
+    # for testing: only process the first two examples as a test
+    # dataset = dataset.select(range(10))
+
+    # load processor
+    if args.greedy:
+        processor = Wav2Vec2Processor.from_pretrained(args.model_id)
+        decoder = None
+    else:
+        processor = Wav2Vec2ProcessorWithLM.from_pretrained(args.model_id)
+        decoder = processor.decoder
+
+    feature_extractor = processor.feature_extractor
+    tokenizer = processor.tokenizer
+
+    # resample audio
+    dataset = dataset.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
+
+    # load eval pipeline
+    if args.device is None:
+        args.device = 0 if torch.cuda.is_available() else -1
+    
+    config = AutoConfig.from_pretrained(args.model_id)
+    model = AutoModelForCTC.from_pretrained(args.model_id)
+    
+    #asr = pipeline("automatic-speech-recognition", model=args.model_id, device=args.device)
+    asr = pipeline("automatic-speech-recognition", config=config, model=model, tokenizer=tokenizer, 
+                   feature_extractor=feature_extractor, decoder=decoder, device=args.device)
+    
+    # build normalizer config
+    tokenizer = AutoTokenizer.from_pretrained(args.model_id)
+    tokens = [x for x in tokenizer.convert_ids_to_tokens(range(0, tokenizer.vocab_size))]
+    special_tokens = [
+        tokenizer.pad_token, tokenizer.word_delimiter_token,
+        tokenizer.unk_token, tokenizer.bos_token,
+        tokenizer.eos_token,
+    ]
+    non_special_tokens = [x for x in tokens if x not in special_tokens]
+    invalid_chars_regex = f"[^\s{re.escape(''.join(set(non_special_tokens)))}]"
+    normalize_to_lower = False
+    for token in non_special_tokens:
+        if token.isalpha() and token.islower():
+            normalize_to_lower = True
+            break
+
+    # map function to decode audio
+    def map_to_pred(batch, args=args, asr=asr, invalid_chars_regex=invalid_chars_regex, normalize_to_lower=normalize_to_lower):
+        prediction = asr(batch["audio"]["array"], chunk_length_s=args.chunk_length_s, stride_length_s=args.stride_length_s)
+
+        batch["prediction"] = prediction["text"]
+        batch["target"] = normalize_text(batch["sentence"], invalid_chars_regex, normalize_to_lower)
+        return batch
+
+    # run inference on all examples
+    result = dataset.map(map_to_pred, remove_columns=dataset.column_names)
+
+    # filtering out empty targets
+    result = result.filter(lambda example: example["target"] != "")
+
+    # compute and log_results
+    # do not change function below
+    log_results(result, args)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--model_id", type=str, required=True, help="Model identifier. Should be loadable with 🤗 Transformers"
+    )
+    parser.add_argument(
+        "--dataset", type=str, required=True, help="Dataset name to evaluate the `model_id`. Should be loadable with 🤗 Datasets"
+    )
+    parser.add_argument(
+        "--config", type=str, required=True, help="Config of the dataset. *E.g.* `'en'`  for Common Voice"
+    )
+    parser.add_argument(
+        "--split", type=str, required=True, help="Split of the dataset. *E.g.* `'test'`"
+    )
+    parser.add_argument(
+        "--chunk_length_s", type=float, default=None, help="Chunk length in seconds. Defaults to None. For long audio files a good value would be 5.0 seconds."
+    )
+    parser.add_argument(
+        "--stride_length_s", type=float, default=None, help="Stride of the audio chunks. Defaults to None. For long audio files a good value would be 1.0 seconds."
+    )
+    parser.add_argument(
+        "--log_outputs", action='store_true', help="If defined, write outputs to log file for analysis."
+    )
+    parser.add_argument(
+        "--greedy", action='store_true', help="If defined, the LM will be ignored during inference."
+    )
+    parser.add_argument(
+        "--device",
+        type=int,
+        default=None,
+        help="The device to run the pipeline on. -1 for CPU (default), 0 for the first GPU and so on.",
+    )
+    args = parser.parse_args()
+
+    main(args)

full_eval.sh

@@ -0,0 +1,15 @@
+# CV 8 - TEST
+
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset mozilla-foundation/common_voice_8_0 --config it --split test --log_outputs --greedy
+mv log_mozilla-foundation_common_voice_8_0_it_test_predictions.txt log_mozilla-foundation_common_voice_8_0_it_test_predictions_greedy.txt
+mv mozilla-foundation_common_voice_8_0_it_test_eval_results.txt mozilla-foundation_common_voice_8_0_it_test_eval_results_greedy.txt
+
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset mozilla-foundation/common_voice_8_0 --config it --split test --log_outputs
+
+# HF EVENT - DEV
+
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset speech-recognition-community-v2/dev_data --config it --split validation --chunk_length_s 5.0 --stride_length_s 1.0 --log_outputs --greedy
+mv log_speech-recognition-community-v2_dev_data_it_validation_predictions.txt log_speech-recognition-community-v2_dev_data_it_validation_predictions_greedy.txt
+mv speech-recognition-community-v2_dev_data_it_validation_eval_results.txt speech-recognition-community-v2_dev_data_it_validation_eval_results_greedy.txt
+
+python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-italian --dataset speech-recognition-community-v2/dev_data --config it --split validation --chunk_length_s 5.0 --stride_length_s 1.0 --log_outputs

language_model/2gram_It_Ref.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f498476811af80757fe360dcae5de0ab06fa73fdec859cbc4e824160129e3540
+size 13061

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 +1,241 @@
+</s>
+<s>
+alba
+alcelisto
+alga
+anca
+anci
+angolo
+anno
+appartamento
+appuntamento
+aprile
+arlo
+arrossamento
+arvi
+attesa
+avviso
+bacio
+badile
+balestra
+bambina
+bandito
+banse
+banzione
+barile
+basilico
+bava
+begnole
+bersaglio
+bicicletta
+bignalo
+bignaso
+binca
+binocolo
+bismacco
+bismaggo
+bismoggo
+bitto
+bivio
+boleggio
+bonifico
+borte
+buongiorno
+caffelatte
+caffetteria
+caffettiera
+cagliralo
+caglivaro
+calderone
+camera
+campagna
+candidato
+candito
+canfrosto
+canile
+capoclasse
+caposcuola
+caposquadra
+cappello
+caregresto
+carnevale
+carnivoro
+cartapesta
+cartellino
+cartellone
+cartoncino
+caso
+cassaforte
+cassetto
+castello
+cava
+ceglirate
+chedinare
+chetinere
+chinadire
+codice
+cofano
+cometa
+compagno
+coragresto
+coregresta
+coritta
+costro
+cuore
+dape
+depe
+destra
+dete
+diga
+diva
+domenica
+dorca
+dorizza
+duna
+ecco
+egnamisa
+egnomisa
+estate
+fame
+fantasma
+farde
+farfalla
+fatto
+fava
+fermaglio
+figlio
+finestra
+flavestro
+flenestro
+flunestro
+foca
+foce
+foga
+foglia
+foglio
+foneggio
+fratello
+frimace
+frutta
+gagliralo
+gatto
+genitore
+gessetto
+gioco
+giostra
+girotondo
+glofeno
+glovelo
+gloveno
+ignemisa
+inquinamento
+insegnamento
+istro
+lada
+larse
+lastra
+lavoro
+lesciacope
+linea
+lonaggio
+machidante
+maestra
+mano
+margherita
+maschera
+matto
+medaglietta
+mela
+meno
+mese
+mezzogiorno
+minestra
+ministra
+mondo
+montagna
+mostra
+motocicletta
+munviglio
+nachipante
+naso
+natura
+nisciacope
+nonno
+notte
+nurto
+nutto
+nuvola
+oblimione
+offesa
+oggi
+ospedale
+ostro
+pace
+pachetenta
+palestra
+pane
+parola
+patto
+pentito
+persona
+personale
+pescespada
+piastra
+polipo
+pomodoro
+poritta
+pradeglia
+pranzo
+presemma
+pressa
+prezzemolo
+prezzo
+prodeglia
+prodiglia
+pronto
+radio
+ranviglio
+risagnera
+risognefa
+risposta
+risugnela
+rofe
+rossetto
+sarvelone
+save
+scarpa
+seca
+signora
+sinistra
+sirfelone
+sirvelone
+soce
+soggiorno
+sollevamento
+sonviglio
+strada
+strage
+strano
+strato
+strega
+strillo
+stringa
+strizza
+strofa
+taglia
+telefono
+tentacolo
+tiglio
+tizio
+tucca
+ustro
+valo
+vaso
+veglia
+ventaglio
+vicino
+vilo
+vizio
+vufebu
+vusciacope
+vuso

mozilla-foundation_common_voice_8_0_it_test_eval_results.txt

@@ -0,0 +1,2 @@
+WER: 0.0675129084844723
+CER: 0.01761353561922042

mozilla-foundation_common_voice_8_0_it_test_eval_results_greedy.txt

@@ -0,0 +1,2 @@
+WER: 0.09043783123819138
+CER: 0.022088713826821264

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 sha256:6330c0527196c61ba8df8fec82234a6e74600018d497018d072d33d4c6b315d2
+size 3850533041

special_tokens_map.json

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

speech-recognition-community-v2_dev_data_it_validation_eval_results.txt

@@ -0,0 +1,2 @@
+WER: 0.15843144982511453
+CER: 0.08932029194181024

speech-recognition-community-v2_dev_data_it_validation_eval_results_greedy.txt

@@ -0,0 +1,2 @@
+WER: 0.23380462091728657
+CER: 0.09411978882213727

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": "|"
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  "'": 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
+}