Upload 5 files

README.md

@@ -1,3 +1,116 @@
 ---
-license: apache-2.0
+language: "en"
+thumbnail:
+pipeline_tag: automatic-speech-recognition
+tags:
+- CTC
+- pytorch
+- speechbrain
+- Transformer
+license: "apache-2.0"
+datasets:
+- commonvoice
+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 trained on CommonVoice English (No LM)
+
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end system pretrained on CommonVoice (English Language) within
+SpeechBrain. For a better experience, we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io). 
+
+The performance of the model is the following:
+
+| Release | Test WER | GPUs |
+|:--------------:|:--------------:| :--------:|
+| 03-06-21 | 15.69 | 2xV100 32GB |
+
+## Pipeline description
+
+This ASR system is composed of 2 different but linked blocks:
+- Tokenizer (unigram) that transforms words into subword units and trained with
+the train transcriptions (train.tsv) of CommonVoice (EN).
+- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([wav2vec2-lv60-large](https://huggingface.co/facebook/wav2vec2-large-lv60)) is combined with two DNN layers and finetuned on CommonVoice En. 
+The obtained final acoustic representation is given to the CTC 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 tranformers and SpeechBrain with the following command:
+
+```
+pip install speechbrain transformers
+```
+
+Please notice that we encourage you to read our tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+### Transcribing your own audio files (in English)
+
+```python
+from speechbrain.pretrained import EncoderDecoderASR
+
+asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-en", savedir="pretrained_models/asr-wav2vec2-commonvoice-en")
+asr_model.transcribe_file("speechbrain/asr-wav2vec2-commonvoice-en/example.wav")
+
+```
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+## Parallel Inference on a Batch
+Please, [see this Colab notebook](https://colab.research.google.com/drive/1hX5ZI9S4jHIjahFCZnhwwQmFoGAi3tmu?usp=sharing) to figure out how to transcribe in parallel a batch of input sentences using a pre-trained model.
+
+### 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/CommonVoice/ASR/seq2seq
+python train.py hparams/train_en_with_wav2vec.yaml --data_folder=your_data_folder
+```
+
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1tjz6IZmVRkuRE97E7h1cXFoGTer7pT73?usp=sharing).
+
+### Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/
+
+
+# **Citing SpeechBrain**
+Please, cite SpeechBrain if you use it for your research or business.
+
+```bibtex
+@misc{speechbrain,
+  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
+  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
+  year={2021},
+  eprint={2106.04624},
+  archivePrefix={arXiv},
+  primaryClass={eess.AS},
+  note={arXiv:2106.04624}
+}
+```

config.json

@@ -0,0 +1,69 @@
+{
+  "speechbrain_interface": "EncoderDecoderASR",
+  "activation_dropout": 0.1,
+  "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": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "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": "4.4.0.dev0",
+  "vocab_size": 32
+}

hyperparams.yaml

@@ -0,0 +1,118 @@
+# ################################
+# Model: wav2vec2 + DNN + CTC/Attention
+# Augmentation: SpecAugment
+# Authors: Titouan Parcollet 2021
+# ################################
+
+sample_rate: 16000
+wav2vec2_hub: facebook/wav2vec2-large-lv60
+
+# BPE parameters
+token_type: unigram  # ["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: 1000  # 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: 10
+eos_threshold: 1.5
+using_max_attn_shift: True
+max_attn_shift: 140
+ctc_weight_decode: 0.0
+temperature: 1.50
+
+enc: !new:speechbrain.lobes.models.VanillaNN.VanillaNN
+    input_shape: [null, null, 1024]
+    activation: !ref <activation>
+    dnn_blocks: !ref <dnn_layers>
+    dnn_neurons: !ref <dnn_neurons>
+
+wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
+    source: !ref <wav2vec2_hub>
+    output_norm: True
+    freeze: True
+    save_path: model_checkpoints
+
+emb: !new:speechbrain.nnet.embedding.Embedding
+    num_embeddings: !ref <output_neurons>
+    embedding_dim: !ref <emb_size>
+
+dec: !new:speechbrain.nnet.RNN.AttentionalRNNDecoder
+    enc_dim: !ref <dnn_neurons>
+    input_size: !ref <emb_size>
+    rnn_type: gru
+    attn_type: location
+    hidden_size: 1024
+    attn_dim: 1024
+    num_layers: 1
+    scaling: 1.0
+    channels: 10
+    kernel_size: 100
+    re_init: True
+    dropout: 0.0
+
+ctc_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <dnn_neurons>
+    n_neurons: !ref <output_neurons>
+
+seq_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <dec_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>
+
+seq_cost: !name:speechbrain.nnet.losses.nll_loss
+    label_smoothing: 0.1
+
+asr_model: !new:torch.nn.ModuleList
+    - [!ref <enc>, !ref <emb>, !ref <dec>, !ref <ctc_lin>, !ref <seq_lin>]
+
+tokenizer: !new:sentencepiece.SentencePieceProcessor
+
+encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
+    wav2vec2: !ref <wav2vec2>
+    enc: !ref <enc>
+
+decoder: !new:speechbrain.decoders.S2SRNNBeamSearcher
+    embedding: !ref <emb>
+    decoder: !ref <dec>
+    linear: !ref <seq_lin>
+    ctc_linear: !ref <ctc_lin>
+    bos_index: !ref <bos_index>
+    eos_index: !ref <eos_index>
+    blank_index: !ref <blank_index>
+    min_decode_ratio: !ref <min_decode_ratio>
+    max_decode_ratio: !ref <max_decode_ratio>
+    beam_size: !ref <beam_size>
+    eos_threshold: !ref <eos_threshold>
+    using_max_attn_shift: !ref <using_max_attn_shift>
+    max_attn_shift: !ref <max_attn_shift>
+    temperature: !ref <temperature>
+
+modules:
+    encoder: !ref <encoder>
+    decoder: !ref <decoder>
+
+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
+}