model upload

.gitattributes

@@ -25,3 +25,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+asr.ckpt filter=lfs diff=lfs merge=lfs -text
+tokenizer.ckpt filter=lfs diff=lfs merge=lfs -text
+wav2vec2.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,132 @@
+---
+language: "dar"
+thumbnail:
+pipeline_tag: automatic-speech-recognition
+tags:
+- CTC
+- pytorch
+- speechbrain
+- Transformer
+license: "apache-2.0"
+datasets:
+- Dvoice
+metrics:
+- wer
+- cer
+---
+
+<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
+<br/><br/>
+
+
+# wav2vec 2.0 with CTC/Attention trained on DVoice Darija (No LM)
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end system pretrained on a [DVoice](https://zenodo.org/record/6342622) Darija dataset within
+SpeechBrain. For a better experience, we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+| DVoice Release | Val. CER | Val. WER | Test CER | Test WER |
+|:-------------:|:---------------------------:| -----:| -----:| -----:|
+| v2.0 | 5.51 | 18.46 | 5.85 | 18.28 |
+
+# Pipeline description
+This ASR system is composed of 2 different but linked blocks:
+- Tokenizer (unigram) that transforms words into subword units and is trained with the train transcriptions.
+- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)) is combined with two DNN layers and finetuned on the Darija dataset.
+The obtained final acoustic representation is given to the CTC greedy decoder.
+The system is trained with recordings sampled at 16kHz (single channel).
+The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed.
+
+# Install SpeechBrain
+First of all, please install transformers and SpeechBrain with the following command:
+```
+pip install speechbrain transformers
+```
+Please notice that we encourage you to read the SpeechBrain tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+# Transcribing your own audio files (in Darija)
+```python
+from speechbrain.pretrained import EncoderASR
+asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-wav2vec2-dvoice-darija", savedir="pretrained_models/asr-wav2vec2-dvoice-darija")
+asr_model.transcribe_file('speechbrain/asr-wav2vec2-dvoice-darija/example_darija.wav')
+```
+
+# Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+### Training
+The model was trained with SpeechBrain.
+To train it from scratch follow these steps:
+1. Clone SpeechBrain:
+```bash
+git clone https://github.com/speechbrain/speechbrain/
+```
+2. Install it:
+```bash
+cd speechbrain
+pip install -r requirements.txt
+pip install -e .
+```
+3. Run Training:
+```bash
+cd recipes/DVoice/ASR/CTC
+python train_with_wav2vec2.py hparams/train_dar_with_wav2vec.yaml --data_folder=/localscratch/darija/
+```
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1vNT7RjRuELs7pumBHmfYsrOp9m46D0ym?usp=sharing).
+
+
+# Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+# Referencing SpeechBrain
+```
+@misc{SB2021,
+    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
+    title = {SpeechBrain},
+    year = {2021},
+    publisher = {GitHub},
+    journal = {GitHub repository},
+    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
+  }
+```
+
+# About DVoice
+DVoice is a community initiative that aims to provide African low resources languages with data and models to facilitate their use of voice technologies. The lack of data on these languages makes it necessary to collect data using methods that are specific to each one. Two different approaches are currently used: the DVoice platforms ([https://dvoice.ma](https://dvoice.ma) and [https://dvoice.sn](https://dvoice.sn)), which are based on Mozilla Common Voice, for collecting authentic recordings from the community, and transfer learning techniques for automatically labeling recordings that are retrieved from social media. The DVoice platform currently manages 7 languages including Darija (Moroccan Arabic dialect) whose dataset appears on this version, Wolof, Mandingo, Serere, Pular, Diola, and Soninke.
+
+For this project, AIOX Labs and the SI2M Laboratory are joining forces to build the future of technologies together.
+
+# About AIOX Labs
+Based in Rabat, London, and Paris, AIOX-Labs mobilizes artificial intelligence technologies to meet the business needs and data projects of companies.
+
+- He is at the service of the growth of groups, the optimization of processes, or the improvement of the customer experience.
+- AIOX-Labs is multi-sector, from fintech to industry, including retail and consumer goods.
+- Business-ready data products with a solid algorithmic base and adaptability for the specific needs of each client.
+- A complementary team made up of doctors in AI and business experts with a solid scientific base and international publications.
+
+Website: [https://www.aiox-labs.com/](https://www.aiox-labs.com/)
+
+# SI2M Laboratory
+The Information Systems, Intelligent Systems, and Mathematical Modeling Research Laboratory (SI2M) is an academic research laboratory of the National Institute of Statistics and Applied Economics (INSEA). The research areas of the laboratories are Information Systems, Intelligent Systems, Artificial Intelligence, Decision Support, Network, and System Security, and Mathematical Modelling.
+
+Website: [SI2M Laboratory](https://insea.ac.ma/index.php/pole-recherche/equipe-de-recherche/150-laboratoire-de-recherche-en-systemes-d-information-systemes-intelligents-et-modelisation-mathematique)
+
+# About SpeechBrain
+SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.
+Website: https://speechbrain.github.io/
+GitHub: https://github.com/speechbrain/speechbrain
+
+
+# Referencing SpeechBrain
+```
+@misc{SB2021,
+    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
+    title = {SpeechBrain},
+    year = {2021},
+    publisher = {GitHub},
+    journal = {GitHub repository},
+    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
+  }
+```
+# Acknowledgements
+This research was supported through computational resources of HPC-MARWAN (www.marwan.ma/hpc) provided by CNRST, Rabat, Morocco. We deeply thank this institution.

asr.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572dbf84bdd480550286b1bc5413f0bb7a457d52121e547c646901b4913cae08
+size 12798880

config.json

@@ -0,0 +1,76 @@
+{
+  "speechbrain_interface": "EncoderASR",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2Model"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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": 0.1,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "transformers_version": "4.5.1",
+  "vocab_size": 32
+}

hyperparams.yaml

@@ -0,0 +1,96 @@
+# ################################
+# Model: wav2vec2 + DNN + CTC/Attention
+# Augmentation: SpecAugment
+# Authors: Titouan Parcollet 2021
+# ################################
+
+sample_rate: 16000
+wav2vec2_hub: facebook/wav2vec2-large-xlsr-53
+
+# BPE parameters
+token_type: char  # ["unigram", "bpe", "char"]
+character_coverage: 1.0
+
+# Model parameters
+activation: !name:torch.nn.LeakyReLU
+dnn_layers: 2
+dnn_neurons: 1024
+emb_size: 128
+dec_neurons: 1024
+
+# Outputs
+output_neurons: 36  # BPE size, index(blank/eos/bos) = 0
+
+# Decoding parameters
+# Be sure that the bos and eos index match with the BPEs ones
+blank_index: 0
+bos_index: 1
+eos_index: 2
+min_decode_ratio: 0.0
+max_decode_ratio: 1.0
+beam_size: 80
+eos_threshold: 1.5
+using_max_attn_shift: True
+max_attn_shift: 140
+ctc_weight_decode: 0.0
+temperature: 1.50
+
+enc: !new:speechbrain.nnet.containers.Sequential
+    input_shape: [null, null, 1024]
+    linear1: !name:speechbrain.nnet.linear.Linear
+        n_neurons: 1024
+        bias: True
+    bn1: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation: !new:torch.nn.LeakyReLU
+    drop: !new:torch.nn.Dropout
+        p: 0.15
+    linear2: !name:speechbrain.nnet.linear.Linear
+        n_neurons: 1024
+        bias: True
+    bn2: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation2: !new:torch.nn.LeakyReLU
+    drop2: !new:torch.nn.Dropout
+        p: 0.15
+    linear3: !name:speechbrain.nnet.linear.Linear
+        n_neurons: 1024
+        bias: True
+    bn3: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation3: !new:torch.nn.LeakyReLU
+
+wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
+    source: !ref <wav2vec2_hub>
+    output_norm: True
+    freeze: True
+    save_path: model_checkpoints
+
+ctc_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <dnn_neurons>
+    n_neurons: !ref <output_neurons>
+
+log_softmax: !new:speechbrain.nnet.activations.Softmax
+    apply_log: True
+
+ctc_cost: !name:speechbrain.nnet.losses.ctc_loss
+    blank_index: !ref <blank_index>
+
+asr_model: !new:torch.nn.ModuleList
+    - [!ref <enc>, !ref <ctc_lin>]
+
+tokenizer: !new:sentencepiece.SentencePieceProcessor
+
+encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
+    wav2vec2: !ref <wav2vec2>
+    enc: !ref <enc>
+    ctc_lin: !ref <ctc_lin>
+
+decoding_function: !name:speechbrain.decoders.ctc_greedy_decode
+    blank_id: !ref <blank_index>
+
+modules:
+    encoder: !ref <encoder>
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        wav2vec2: !ref <wav2vec2>
+        asr: !ref <asr_model>
+        tokenizer: !ref <tokenizer>

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

tokenizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99392f1c87d21e28b1f88989db9af8f04d2fa06b45f6c5edb6b1d2257758a2da
+size 238116

wav2vec2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f502d9cc309400c4b8116b80969470578f6628100e0d45ab046f9e1e990076
+size 1261920693