Integrating Pruned Fast RNNT with Transducer + new recipe for mTEDx dataset

recipes/CommonVoice/ASR/transducer/hparams/train_fr.yaml

@@ -183,7 +183,7 @@ log_softmax: !new:speechbrain.nnet.activations.Softmax
    apply_log: True
 
 transducer_cost: !name:speechbrain.nnet.losses.transducer_loss
-   use_torchaudio: True
+   framework: torchaudio
    blank_index: !ref <blank_index>
 
 # for MTL

recipes/LibriSpeech/ASR/transducer/hparams/train.yaml

@@ -190,7 +190,7 @@ log_softmax: !new:speechbrain.nnet.activations.Softmax
 
 transducer_cost: !name:speechbrain.nnet.losses.transducer_loss
    blank_index: !ref <blank_index>
-   use_torchaudio: True
+   framework: torchaudio
 
 # This is the RNNLM that is used according to the Huggingface repository
 # NB: It has to match the pre-trained RNNLM!!

recipes/TIMIT/ASR/transducer/hparams/train.yaml

@@ -150,7 +150,7 @@ output: !new:speechbrain.nnet.linear.Linear
 #    apply_log: True
 
 compute_cost: !name:speechbrain.nnet.losses.transducer_loss
-    use_torchaudio: True
+    framework: torchaudio
     blank_index: !ref <blank_index>
 
 model: !new:torch.nn.ModuleList [[
@@ -216,7 +216,7 @@ train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
 
 transducer_stats: !name:speechbrain.utils.metric_stats.MetricStats
     metric: !name:speechbrain.nnet.losses.transducer_loss
-        use_torchaudio: True
+        framework: torchaudio
         blank_index: !ref <blank_index>
         reduction: none
 

recipes/TIMIT/ASR/transducer/hparams/train_wav2vec.yaml

@@ -133,7 +133,7 @@ output: !new:speechbrain.nnet.linear.Linear
 #    apply_log: True
 
 compute_cost: !name:speechbrain.nnet.losses.transducer_loss
-    use_torchaudio: True
+    framework: torchaudio
     blank_index: !ref <blank_index>
 
 model: !new:torch.nn.ModuleList [[
@@ -205,7 +205,7 @@ train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
 
 transducer_stats: !name:speechbrain.utils.metric_stats.MetricStats
     metric: !name:speechbrain.nnet.losses.transducer_loss
-        use_torchaudio: True
+        framework: torchaudio
         blank_index: !ref <blank_index>
         reduction: none
 

recipes/mTEDx/ASR/CTC/README.md

@@ -0,0 +1,47 @@
+# mTEDx ASR with CTC models.
+This folder contains the scripts to train a wav2vec based system using mTEDx. You can train either a single-language wav2vec model or multilingual
+wav2vec model. Before running this recipe, make sure to read this [README](../../README.md) file first.
+
+**Note:**\
+Wav2vec model used in this recipe is pre-trained on the French language.
+In order to use another language, don't forget to change the `wav2vec2_hub`
+in the `train_wav2vec.yaml` YAML file.
+
+
+# How to run
+
+To train a single-language wav2vec model, run:
+```bash
+$ python train.py hparams/train_wav2vec.yaml
+```
+
+To train a multilingual wav2vec model, run:
+```bash
+$ python train.py hparams/train_xlsr.yaml
+```
+
+# Results
+
+TODO
+
+
+# **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}
+}
+```

recipes/mTEDx/ASR/CTC/hparams/train_wav2vec.yaml

@@ -0,0 +1,175 @@
+# ################################
+# Model: wav2vec2 + DNN + CTC
+# Authors: Titouan Parcollet 2021
+#          Mohamed Anwar 2022
+# ################################
+
+# Seed needs to be set at top of yaml, before objects with parameters are made
+seed: 1234
+__set_seed: !!python/object/apply:torch.manual_seed [!ref <seed>]
+output_folder: !PLACEHOLDER
+wer_file: !ref <output_folder>/wer.txt
+save_folder: !ref <output_folder>/save
+train_log: !ref <output_folder>/train_log.txt
+
+# URL for the biggest LeBenchmark wav2vec french.
+wav2vec2_hub: LeBenchmark/wav2vec2-FR-7K-large
+
+# Data files
+data_folder: !PLACEHOLDER
+langs:
+   - fr
+remove_punc_cap: True # remove punctuation & capitalization from text
+
+train_json: !ref <data_folder>/train_fr.json
+valid_json: !ref <data_folder>/valid_fr.json
+test_json: !ref <data_folder>/test_fr.json
+
+# We remove train utterances longer than 10s
+avoid_if_longer_than: 20.0
+test_lang: fr
+
+# Training parameters
+number_of_epochs: 30
+number_of_ctc_epochs: 15
+lr: 1.0
+lr_wav2vec: 0.0001
+ctc_weight: 0.3
+sorting: descending # ascending, descending
+auto_mix_prec: True
+sample_rate: 16000
+max_grad_norm: -1
+
+batch_size: 4
+batch_size_valid: 2 #for valid & test
+
+train_dataloader_opts:
+   batch_size: !ref <batch_size>
+   num_workers: 4
+
+valid_dataloader_opts:
+   batch_size: !ref <batch_size_valid>
+   num_workers: 4
+
+test_dataloader_opts:
+   batch_size: !ref <batch_size_valid>
+   num_workers: 4
+
+# BPE parameters
+token_type: char  # ["unigram", "bpe", "char"]
+character_coverage: 1.0
+
+# Model parameters
+activation: !name:torch.nn.LeakyReLU
+wav2vec_output_dim: 1024
+dnn_neurons: 1024
+freeze_wav2vec: False
+
+# Outputs
+output_neurons: 161  # 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
+
+#
+# Functions and classes
+#
+epoch_counter: !new:speechbrain.utils.epoch_loop.EpochCounter
+   limit: !ref <number_of_epochs>
+
+enc: !new:speechbrain.nnet.containers.Sequential
+   input_shape: [null, null, !ref <wav2vec_output_dim>]
+   linear1: !name:speechbrain.nnet.linear.Linear
+      n_neurons: <dnn_neurons>
+      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: <dnn_neurons>
+      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: <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: !ref <save_folder>/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>
+
+modules:
+   wav2vec2: !ref <wav2vec2>
+   enc: !ref <enc>
+   ctc_lin: !ref <ctc_lin>
+
+model: !new:torch.nn.ModuleList
+   - [!ref <enc>, !ref <ctc_lin>]
+
+model_opt_class: !name:torch.optim.Adadelta
+   lr: !ref <lr>
+   rho: 0.95
+   eps: 1.e-8
+
+wav2vec_opt_class: !name:torch.optim.Adam
+   lr: !ref <lr_wav2vec>
+
+lr_annealing_model: !new:speechbrain.nnet.schedulers.NewBobScheduler
+   initial_value: !ref <lr>
+   improvement_threshold: 0.0025
+   annealing_factor: 0.8
+   patient: 0
+
+lr_annealing_wav2vec: !new:speechbrain.nnet.schedulers.NewBobScheduler
+   initial_value: !ref <lr_wav2vec>
+   improvement_threshold: 0.0025
+   annealing_factor: 0.9
+   patient: 0
+
+checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
+   checkpoints_dir: !ref <save_folder>
+   recoverables:
+      wav2vec2: !ref <wav2vec2>
+      model: !ref <model>
+      scheduler_model: !ref <lr_annealing_model>
+      scheduler_wav2vec: !ref <lr_annealing_wav2vec>
+      counter: !ref <epoch_counter>
+
+train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
+   save_file: !ref <train_log>
+
+tensorboard_logger: !new:speechbrain.utils.train_logger.TensorboardLogger
+   save_dir: !ref <output_folder>/logs
+
+error_rate_computer: !name:speechbrain.utils.metric_stats.ErrorRateStats
+
+cer_computer: !name:speechbrain.utils.metric_stats.ErrorRateStats
+   split_tokens: True