new org name

README.md

@@ -0,0 +1,78 @@
+---
+language: "en"
+thumbnail:
+tags:
+- ASR
+- CTC
+- Attention
+- pytorch
+license: "apache-2.0"
+datasets:
+- librispeech
+metrics:
+- wer
+- cer
+---
+
+# CRDNN with CTC/Attention and RNNLM trained on LibriSpeech
+
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end system pretrained on LibriSpeech (EN) within
+SpeechBrain. For a better experience we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io). The given ASR model performance are:
+
+| Release | Test WER | GPUs |
+|:-------------:|:--------------:| :--------:|
+| 20-05-22 | 3.08 | 1xV100 32GB |
+
+## Pipeline description
+
+This ASR system is composed with 3 different but linked blocks:
+1. Tokenizer (unigram) that transforms words into subword units and trained with
+the train transcriptions of LibriSpeech.
+2. Neural language model (RNNLM) trained on the full 10M words dataset.
+3. Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of
+N blocks of convolutional neural networks with normalisation and pooling on the
+frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain
+the final acoustic representation that is given to the CTC and attention decoders.
+
+## Intended uses & limitations
+
+This model has been primilarly developed to be run within SpeechBrain as a pretrained ASR model
+for the english language. Thanks to the flexibility of SpeechBrain, any of the 3 blocks
+detailed above can be extracted and connected to you custom pipeline as long as SpeechBrain is
+installed.
+
+## Install SpeechBrain
+
+First of all, please install SpeechBrain with the following command:
+
+```
+pip install \\we hide ! SpeechBrain is still private :p
+```
+
+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 EncoderDecoderASR
+
+asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-rnnlm-librispeech")
+asr_model.transcribe_file("path_to_your_file.wav")
+
+```
+
+#### 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}},
+  }
+```

asr.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e795c7e18f3bab6bd5f47060ab852233deb33d7d550e989994c8683901e18d5
+size 479555971

hyperparams.yaml

@@ -0,0 +1,153 @@
+# ############################################################################
+# Model: E2E ASR with attention-based ASR
+# Encoder: CRDNN model
+# Decoder: GRU + beamsearch + RNNLM
+# Tokens: BPE with unigram
+# Authors:  Ju-Chieh Chou, Mirco Ravanelli, Abdel Heba, Peter Plantinga 2020
+# ############################################################################
+
+
+# Feature parameters
+sample_rate: 16000
+n_fft: 400
+n_mels: 40
+
+# Model parameters
+activation: !name:torch.nn.LeakyReLU
+dropout: 0.15
+cnn_blocks: 2
+cnn_channels: (128, 256)
+inter_layer_pooling_size: (2, 2)
+cnn_kernelsize: (3, 3)
+time_pooling_size: 4
+rnn_class: !name:speechbrain.nnet.RNN.LSTM
+rnn_layers: 4
+rnn_neurons: 1024
+rnn_bidirectional: True
+dnn_blocks: 2
+dnn_neurons: 512
+emb_size: 128
+dec_neurons: 1024
+output_neurons: 1000  # index(blank/eos/bos) = 0
+blank_index: 0
+
+# Decoding parameters
+bos_index: 0
+eos_index: 0
+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: 240
+lm_weight: 0.50
+coverage_penalty: 1.5
+temperature: 1.25
+temperature_lm: 1.25
+
+normalize: !new:speechbrain.processing.features.InputNormalization
+    norm_type: global
+
+compute_features: !new:speechbrain.lobes.features.Fbank
+    sample_rate: !ref <sample_rate>
+    n_fft: !ref <n_fft>
+    n_mels: !ref <n_mels>
+
+enc: !new:speechbrain.lobes.models.CRDNN.CRDNN
+    input_shape: [null, null, !ref <n_mels>]
+    activation: !ref <activation>
+    dropout: !ref <dropout>
+    cnn_blocks: !ref <cnn_blocks>
+    cnn_channels: !ref <cnn_channels>
+    cnn_kernelsize: !ref <cnn_kernelsize>
+    inter_layer_pooling_size: !ref <inter_layer_pooling_size>
+    time_pooling: True
+    using_2d_pooling: False
+    time_pooling_size: !ref <time_pooling_size>
+    rnn_class: !ref <rnn_class>
+    rnn_layers: !ref <rnn_layers>
+    rnn_neurons: !ref <rnn_neurons>
+    rnn_bidirectional: !ref <rnn_bidirectional>
+    rnn_re_init: True
+    dnn_blocks: !ref <dnn_blocks>
+    dnn_neurons: !ref <dnn_neurons>
+
+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: !ref <dec_neurons>
+    attn_dim: 1024
+    num_layers: 1
+    scaling: 1.0
+    channels: 10
+    kernel_size: 100
+    re_init: True
+    dropout: !ref <dropout>
+
+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
+
+lm_model: !new:speechbrain.lobes.models.RNNLM.RNNLM
+    output_neurons: !ref <output_neurons>
+    embedding_dim: !ref <emb_size>
+    activation: !name:torch.nn.LeakyReLU
+    dropout: 0.0
+    rnn_layers: 2
+    rnn_neurons: 2048
+    dnn_blocks: 1
+    dnn_neurons: 512
+    return_hidden: True  # For inference
+
+tokenizer: !new:sentencepiece.SentencePieceProcessor
+
+asr_model: !new:torch.nn.ModuleList
+    - [!ref <enc>, !ref <emb>, !ref <dec>, !ref <ctc_lin>, !ref <seq_lin>]
+
+beam_searcher: !new:speechbrain.decoders.S2SRNNBeamSearchLM
+    embedding: !ref <emb>
+    decoder: !ref <dec>
+    linear: !ref <seq_lin>
+    language_model: !ref <lm_model>
+    bos_index: !ref <bos_index>
+    eos_index: !ref <eos_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>
+    coverage_penalty: !ref <coverage_penalty>
+    lm_weight: !ref <lm_weight>
+    temperature: !ref <temperature>
+    temperature_lm: !ref <temperature_lm>
+
+
+modules:
+    compute_features: !ref <compute_features>
+    normalize: !ref <normalize>
+    asr_model: !ref <asr_model>
+    asr_encoder: !ref <enc>
+    asr_decoder: !ref <dec>
+    lm_model: !ref <lm_model>
+    beam_searcher: !ref <beam_searcher>
+
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        asr: !ref <asr_model>
+        lm: !ref <lm_model>
+        tokenizer: !ref <tokenizer>

lm.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f73e243f5f0eb070a05a2069ba5b9014232e926384cc7d5ba24cde060c84997
+size 212420087

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11bfd7dbe13a266d13c00f6ff042a00fdbd40f3f5973928f9b49c33da32b512
+size 1409

tokenizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a6cba34cd520b33fd83612d5efc8ba7e351166541eb2726642bb3032234d31
+size 253217