add wav2vec2 model

.gitattributes

@@ -30,3 +30,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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

@@ -1,3 +1,114 @@
 ---
+language:
+- en
+thumbnail: null
+pipeline_tag: automatic-speech-recognition
+tags:
+- CTC
+- pytorch
+- speechbrain
 license: apache-2.0
+datasets:
+- switchboard
+metrics:
+- wer
+- ser
+
 ---
+
+<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 Switchboard (No LM)
+
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end system pretrained on the Switchboard corpus 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  | Swbd SER | Callhome SER | Eval2000 SER | Swbd WER | Callhome WER | Eval2000 WER | GPUs        |
+|:--------:|:--------:|:------------:|:------------:|:--------:|:------------:|:------------:|:-----------:|
+| 17-09-22 |  48.60   |  55.76       |   52.96      |  8 .76   |  14.67       |     11.78    | 4xA100 40GB |
+
+## Pipeline description
+
+This ASR system is composed of 2 different but linked blocks:
+- Tokenizer (unigram) that transforms words into subword units trained on the Switchboard training transcripts and the Fisher corpus.
+- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60)) is combined with two DNN layers and finetuned on Switchboard
+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 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
+
+```python
+from speechbrain.pretrained import EncoderASR
+
+asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-switchboard", savedir="pretrained_models/asr-wav2vec2-switchboard")
+asr_model.transcribe_file('path/to/audiofile')
+
+```
+### 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 (Commit hash: '70904d0').
+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/Switchboard/ASR/CTC/
+python train_with_wav2vec.py hparams/train_with_wav2vec.yaml --data_folder=your_data_folder
+```
+
+### 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 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
+
+
+
+

asr.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d3f9494dd14d52e67de937f7aeec89f1fb6f3376827d4f66a3ae45dfc03166
+size 16751264

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 +1,88 @@
+# ################################
+# Model: wav2vec2 + DNN + CTC
+# Augmentation: SpecAugment
+# Authors: Titouan Parcollet 2021, Dominik Wagner 2022
+# ################################
+
+wav2vec2_hub: facebook/wav2vec2-large-lv60
+sample_rate: 16000
+
+# BPE parameters
+token_type: unigram  # ["unigram", "bpe", "char"]
+character_coverage: 1.0
+
+# Model parameters
+wav2vec_output_dim: 1024
+dnn_neurons: 1024
+freeze_wav2vec: False
+dropout: 0.15
+
+# 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
+
+enc: !new:speechbrain.nnet.containers.Sequential
+  input_shape: [null, null, !ref <wav2vec_output_dim>]
+  linear1: !name:speechbrain.nnet.linear.Linear
+    n_neurons: !ref <dnn_neurons>
+    bias: True
+  bn1: !name:speechbrain.nnet.normalization.BatchNorm1d
+  activation: !new:torch.nn.LeakyReLU
+  drop: !new:torch.nn.Dropout
+    p: !ref <dropout>
+  linear2: !name:speechbrain.nnet.linear.Linear
+    n_neurons: !ref <dnn_neurons>
+    bias: True
+  bn2: !name:speechbrain.nnet.normalization.BatchNorm1d
+  activation2: !new:torch.nn.LeakyReLU
+  drop2: !new:torch.nn.Dropout
+    p: !ref <dropout>
+  linear3: !name:speechbrain.nnet.linear.Linear
+    n_neurons: !ref <dnn_neurons>
+    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: !ref <freeze_wav2vec>
+  save_path: wav2vec2_checkpoint
+
+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>
+
+modules:
+  encoder: !ref <encoder>
+
+decoding_function: !name:speechbrain.decoders.ctc_greedy_decode
+    blank_id: !ref <blank_index>
+
+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 sha256:17667ee5f627ce940fb671258a9340e12875fa9b02476061112df250bee538f4
+size 253486

wav2vec2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f7c5b9cb72a46f606315c49232b5bb4a7d055196c843a95445c74402fa1794
+size 1261923125