SoundChoice G2P: Initial model import

.gitattributes

@@ -29,3 +29,5 @@ 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
+ctc_lin.ckpt filter=lfs diff=lfs merge=lfs -text
+model.ckpt filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,3 +1,103 @@
 ---
 license: apache-2.0
 ---
+# SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation
+
+This repository provides all the necessary tools to perform English grapheme-to-phoneme conversion with a pretrained SoundChoice G2P model using SpeechBrain. It is trained on LibriG2P training data derived from [LibriSpeech Alignments](https://zenodo.org/record/2619474#.YuCdaC8r1ZF) and [Google Wikipedia](https://github.com/google/WikipediaHomographData)
+
+
+## Install SpeechBrain
+
+First of all, please install SpeechBrain with the following command:
+
+```bash
+pip install speechbrain
+```
+
+Please notice that we encourage you to read our tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+## Perform G2P Conversion
+
+Please follow the example below to perform grapheme-to-phoneme conversion with a high-level wrapper.
+
+```python
+from speechbrain.pretrained import GraphemeToPhoneme
+g2p = GraphemeToPhoneme.from_hparams("speechbrain/soundchoice-g2p")
+text = "To be or not to be, that is the question"
+phonemes = g2p(text)
+```
+
+Given below is the expected output
+```python
+>>> phonemes
+['T', 'UW', ' ', 'B', 'IY', ' ', 'AO', 'R', ' ', 'N', 'AA', 'T', ' ', 'T', 'UW', ' ', 'B', 'IY', ' ', 'DH', 'AE', 'T', ' ', 'IH', 'Z', ' ', 'DH', 'AH', ' ', 'K', 'W', 'EH', 'S', 'CH', 'AH', 'N']
+```
+
+To perform G2P conversion on a batch of text, pass
+an array of strings to the interface:
+
+```python
+items = [
+    "All's Well That Ends Well",
+    "The Merchant of Venice",
+    "The Two Gentlemen of Verona",
+    "The Comedy of Errors"
+]
+transcriptions = g2p(items)
+```
+
+Given below is the expected output:
+
+```python
+>>> transcriptions
+[['AO', 'L', 'Z', ' ', 'W', 'EH', 'L', ' ', 'DH', 'AE', 'T', ' ', 'EH', 'N', 'D', 'Z', ' ', 'W', 'EH', 'L'], ['DH', 'AH', ' ', 'M', 'ER', 'CH', 'AH', 'N', 'T', ' ', 'AH', 'V', ' ', 'V', 'EH', 'N', 'AH', 'S'], ['DH', 'AH', ' ', 'T', 'UW', ' ', 'JH', 'EH', 'N', 'T', 'AH', 'L', 'M', 'IH', 'N', ' ', 'AH', 'V', ' ', 'V', 'ER', 'OW', 'N', 'AH'], ['DH', 'AH', ' ', 'K', 'AA', 'M', 'AH', 'D', 'IY', ' ', 'AH', 'V', ' ', 'EH', 'R', 'ER', 'Z']]
+```
+
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+### Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+### Training
+The model was trained with SpeechBrain (aa018540).
+To train it from scratch follows these steps:
+1. Clone SpeechBrain:
+```bash
+git clone https://github.com/speechbrain/speechbrain/
+```
+2. Install it:
+```
+cd speechbrain
+pip install -r requirements.txt
+pip install -e .
+```
+
+3. Run Training:
+```
+cd recipes/LibriSpeech/G2P
+python train.py hparams/hparams_g2p_rnn.yaml --data_folder=your_data_folder
+```
+
+Adjust hyperparameters as needed by passing additional arguments.
+
+# **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}
+}
+```
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

ctc_lin.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c72639caba01630cf5ccc9b287b6eb7b79acc2276aa6f5cc23640640ac8f7ee
+size 177319

hyperparams.yaml

@@ -0,0 +1,507 @@
+# Generated 2022-07-09 from:
+# /notebooks/speechbrain/recipes/LibriSpeech/G2P/hparams/hparams_g2p_rnn.yaml
+# yamllint disable
+# ################################
+# Model: LSTM (encoder) + GRU (decoder) (tokenized)
+# Authors:
+# Loren Lugosch & Mirco Ravanelli 2020
+# Artem Ploujnikov 2021
+# ################################
+
+# Seed needs to be set at top of yaml, before objects with parameters are made
+seed: 1234
+__set_seed: !apply:torch.manual_seed [1234]
+
+
+# Tokenizers
+char_tokenize: false
+char_token_type: unigram  # ["unigram", "bpe", "char"]
+char_token_output: 512
+char_token_wordwise: true
+phn_tokenize: false
+phn_token_type: unigram  # ["unigram", "bpe", "char"]
+phn_token_output: 512  # index(blank/eos/bos/unk) = 0
+phn_token_wordwise: true
+character_coverage: 1.0
+
+
+phonemes_count: 43
+graphemes_count: 31
+phonemes_enable_space: true
+
+# Training Parameters
+lexicon_epochs: 50
+lexicon_ctc_epochs: 10
+lexicon_limit_to_stop: 50                    # No stopping by default, can override
+lexicon_limit_warmup: 50                    # No stopping by default, can override
+sentence_epochs: 13
+sentence_ctc_epochs: 10
+sentence_limit_to_stop: 3
+sentence_limit_warmup: 3
+homograph_epochs: 50
+homograph_ctc_epochs: 10
+homograph_limit_to_stop: 5
+homograph_limit_warmup: 10
+lexicon_batch_size: 1024
+sentence_batch_size: 32
+homograph_batch_size: 32
+ctc_weight: 0.5
+homograph_loss_weight: 2.0
+lr: 0.002
+save_for_pretrained: true
+
+# Model parameters
+output_neurons: &id004 !apply:speechbrain.utils.hparams.choice
+
+  value: false
+  choices:
+    true: 513
+    false: 43
+
+enc_num_embeddings: &id005 !apply:speechbrain.utils.hparams.choice
+  value: false
+  choices:
+    true: 513
+    false: 31
+
+enc_dropout: 0.5
+enc_neurons: 512
+enc_num_layers: 4
+dec_dropout: 0.5
+dec_neurons: 512
+dec_att_neurons: 256
+dec_num_layers: 4
+embedding_dim: 512
+
+# Determines whether to use BOS (beginning-of-sequence) or EOS (end-of-sequence) tokens
+# Available modes:
+# raw: no BOS/EOS tokens are added
+# bos: a beginning-of-sequence token is added
+# eos: an end-of-sequence token is added
+grapheme_sequence_mode: bos
+phoneme_sequence_mode: bos
+
+
+# Special Token information
+bos_index: 0
+eos_index: 1
+blank_index: 2
+unk_index: 2
+token_space_index: 512
+
+
+# Language Model
+lm_emb_dim: 256 # dimension of the embeddings
+lm_rnn_size: 512 # dimension of hidden layers
+lm_layers: 2 # number of hidden layers
+lm_output_neurons: 43
+
+# Beam Searcher
+use_language_model: false
+beam_search_min_decode_ratio: 0
+beam_search_max_decode_ratio: 1.0
+beam_search_beam_size: 16
+beam_search_beam_size_valid: 16
+beam_search_eos_threshold: 10.0
+beam_search_using_max_attn_shift: false
+beam_search_max_attn_shift: 10
+beam_search_coverage_penalty: 5.0
+beam_search_lm_weight: 0.5
+beam_search_ctc_weight_decode: 0.4
+beam_search_temperature: 1.25
+beam_search_temperature_lm: 1.0
+
+# Word embeddings
+use_word_emb: true
+word_emb_model: bert-base-uncased
+word_emb_dim: 768
+word_emb_enc_dim: 256
+word_emb_norm_type: batch
+
+graphemes: &id028
+- A
+- B
+- C
+- D
+- E
+- F
+- G
+- H
+- I
+- J
+- K
+- L
+- M
+- N
+- O
+- P
+- Q
+- R
+- S
+- T
+- U
+- V
+- W
+- X
+- Y
+- Z
+- "'"
+- ' '
+
+phonemes: &id001
+
+
+- AA
+- AE
+- AH
+- AO
+- AW
+- AY
+- B
+- CH
+- D
+- DH
+- EH
+- ER
+- EY
+- F
+- G
+- HH
+- IH
+- IY
+- JH
+- K
+- L
+- M
+- N
+- NG
+- OW
+- OY
+- P
+- R
+- S
+- SH
+- T
+- TH
+- UH
+- UW
+- V
+- W
+- Y
+- Z
+- ZH
+- ' '
+
+enc_input_dim: &id003 !apply:speechbrain.lobes.models.g2p.model.input_dim
+  use_word_emb: true
+  word_emb_enc_dim: 256
+  embedding_dim: 512
+
+
+phn_char_map: &id002 !apply:speechbrain.lobes.models.g2p.dataio.build_token_char_map
+
+
+# Models
+  tokens: *id001
+char_phn_map: &id023 !apply:speechbrain.lobes.models.g2p.dataio.flip_map
+  map_dict: *id002
+enc: &id006 !new:speechbrain.nnet.RNN.LSTM
+  input_shape: [null, null, *id003]
+  bidirectional: true
+  hidden_size: 512
+  num_layers: 4
+  dropout: 0.5
+
+lin: &id010 !new:speechbrain.nnet.linear.Linear
+  input_size: 512
+  n_neurons: *id004
+  bias: false
+
+ctc_lin: &id013 !new:speechbrain.nnet.linear.Linear
+  input_size: 1024
+  n_neurons: *id004
+encoder_emb: &id007 !new:speechbrain.nnet.embedding.Embedding
+  num_embeddings: *id005
+  embedding_dim: 512
+
+emb: &id008 !new:speechbrain.nnet.embedding.Embedding
+  num_embeddings: *id004
+  embedding_dim: 512
+
+dec: &id009 !new:speechbrain.nnet.RNN.AttentionalRNNDecoder
+  enc_dim: 1024
+  input_size: 512
+  rnn_type: gru
+  attn_type: content
+  dropout: 0.5
+  hidden_size: 512
+  attn_dim: 256
+  num_layers: 4
+
+word_emb_enc: &id012 !new:speechbrain.lobes.models.g2p.model.WordEmbeddingEncoder
+
+  word_emb_dim: 768
+  word_emb_enc_dim: 256
+  norm_type: batch
+
+word_emb: !apply:speechbrain.lobes.models.g2p.dataio.lazy_init
+  init: !name:speechbrain.wordemb.transformer.TransformerWordEmbeddings
+    model: bert-base-uncased
+
+log_softmax: &id011 !new:speechbrain.nnet.activations.Softmax
+  apply_log: true
+
+modules:
+  model: &id014 !new:speechbrain.lobes.models.g2p.model.AttentionSeq2Seq
+    enc: *id006
+    encoder_emb: *id007
+    emb: *id008
+    dec: *id009
+    lin: *id010
+    out: *id011
+    use_word_emb: true
+    word_emb_enc: *id012
+  enc: *id006
+  encoder_emb: *id007
+  emb: *id008
+  dec: *id009
+  lin: *id010
+  ctc_lin: *id013
+  out: *id011
+  word_emb:
+  word_emb_enc: *id012
+model: *id014
+lm_model: &id015 !new:speechbrain.lobes.models.RNNLM.RNNLM
+  embedding_dim: 256
+  rnn_layers: 2
+  rnn_neurons: 512
+  output_neurons: 43
+  return_hidden: true
+
+opt_class: !name:torch.optim.Adam
+  lr: 0.002
+
+beam_searcher: &id029 !new:speechbrain.decoders.S2SRNNBeamSearcher
+  embedding: *id008
+  decoder: *id009
+  linear: *id010
+  ctc_linear: *id013
+  bos_index: 0
+  eos_index: 1
+  blank_index: 2
+  min_decode_ratio: 0
+  max_decode_ratio: 1.0
+  beam_size: 16
+  eos_threshold: 10.0
+  using_max_attn_shift: false
+  max_attn_shift: 10
+  coverage_penalty: 5.0
+  ctc_weight: 0.4
+
+beam_searcher_valid: !new:speechbrain.decoders.S2SRNNBeamSearcher
+  embedding: *id008
+  decoder: *id009
+  linear: *id010
+  ctc_linear: *id013
+  bos_index: 0
+  eos_index: 1
+  blank_index: 2
+  min_decode_ratio: 0
+  max_decode_ratio: 1.0
+  beam_size: 16
+  eos_threshold: 10.0
+  using_max_attn_shift: false
+  max_attn_shift: 10
+  coverage_penalty: 5.0
+  ctc_weight: 0.4
+
+beam_searcher_lm: !new:speechbrain.decoders.seq2seq.S2SRNNBeamSearchLM
+  embedding: *id008
+  decoder: *id009
+  linear: *id010
+  ctc_linear: *id013
+  language_model: *id015
+  bos_index: 0
+  eos_index: 1
+  blank_index: 2
+  min_decode_ratio: 0
+  max_decode_ratio: 1.0
+  beam_size: 16
+  eos_threshold: 10.0
+  using_max_attn_shift: false
+  max_attn_shift: 10
+  coverage_penalty: 5.0
+  ctc_weight: 0.4
+  lm_weight: 0.5
+  temperature: 1.25
+  temperature_lm: 1.0
+
+
+lr_annealing: &id018 !new:speechbrain.nnet.schedulers.NewBobScheduler
+  initial_value: 0.002
+  improvement_threshold: 0.0
+  annealing_factor: 0.8
+  patient: 0
+
+homograph_extractor: !new:speechbrain.lobes.models.g2p.homograph.SubsequenceExtractor
+
+seq_cost: &id016 !name:speechbrain.nnet.losses.nll_loss
+
+  label_smoothing: 0.1
+
+ctc_cost: !name:speechbrain.nnet.losses.ctc_loss
+  blank_index: 2
+
+seq_cost_metric: &id017 !name:speechbrain.nnet.losses.nll_loss
+
+  label_smoothing: 0.1
+  reduction: batch
+
+homograph_cost: !new:speechbrain.lobes.models.g2p.homograph.SubsequenceLoss
+  seq_cost: *id016
+seq_stats: !name:speechbrain.utils.metric_stats.MetricStats
+  metric: *id017
+seq_stats_homograph: !name:speechbrain.utils.metric_stats.MetricStats
+  metric: *id017
+classification_stats_homograph: !name:speechbrain.utils.metric_stats.ClassificationStats
+
+per_stats: !name:speechbrain.utils.metric_stats.ErrorRateStats
+per_stats_homograph: !name:speechbrain.utils.metric_stats.ErrorRateStats
+
+
+model_output_keys:
+- p_seq
+- char_lens
+- encoder_out
+
+grapheme_encoder: &id027 !new:speechbrain.dataio.encoder.TextEncoder
+phoneme_encoder: &id024 !new:speechbrain.dataio.encoder.TextEncoder
+
+
+grapheme_tokenizer: !apply:speechbrain.lobes.models.g2p.dataio.lazy_init
+  init: !name:speechbrain.tokenizers.SentencePiece.SentencePiece
+    model_dir: grapheme_tokenizer
+    bos_id: 0
+    eos_id: 1
+    unk_id: 2
+    vocab_size: 512
+    annotation_train: tokenizer_annotation_train.json
+    annotation_read: char
+    model_type: unigram                    # ["unigram", "bpe", "char"]
+    character_coverage: 1.0
+    annotation_format: json
+    text_file: grapheme_annotations.txt
+
+phoneme_tokenizer: &id022 !apply:speechbrain.lobes.models.g2p.dataio.lazy_init
+  init: !name:speechbrain.tokenizers.SentencePiece.SentencePiece
+    model_dir: phoneme_tokenizer
+    bos_id: 0
+    eos_id: 1
+    unk_id: 2
+    vocab_size: 512
+    annotation_train: tokenizer_annotation_train.json
+    annotation_read: phn
+    model_type: unigram                   # ["unigram", "bpe", "char"]
+    character_coverage: 1.0
+    annotation_list_to_check: [tokenizer_annotation_valid.json]
+    annotation_format: json
+    text_file: phoneme_annotations.txt
+
+out_phoneme_decoder_tok: &id025 !apply:speechbrain.lobes.models.g2p.dataio.char_map_detokenize
+  tokenizer: *id022
+  char_map: *id023
+  token_space_index: 512
+  wordwise: true
+
+out_phoneme_decoder_raw: &id026 !name:speechbrain.lobes.models.g2p.dataio.text_decode
+
+  encoder: *id024
+out_phoneme_decoder: !apply:speechbrain.utils.hparams.choice
+  value: false
+  choices:
+    true: *id025
+    false: *id026
+encode_pipeline:
+  batch: false
+  use_padded_data: true
+  output_keys:
+  - grapheme_list
+  - grapheme_encoded_list
+  - grapheme_encoded
+  - word_emb
+  init:
+  - func: !name:speechbrain.lobes.models.g2p.dataio.enable_eos_bos
+      encoder: *id027
+      tokens: *id028
+      bos_index: 0
+      eos_index: 1
+  - func: !name:speechbrain.lobes.models.g2p.dataio.enable_eos_bos
+      encoder: *id024
+      tokens: *id001
+      bos_index: 0
+      eos_index: 1
+  steps:
+  - func: !name:speechbrain.lobes.models.g2p.dataio.clean_pipeline
+      graphemes: *id028
+    takes: txt
+    provides: txt_cleaned
+  - func: !name:speechbrain.lobes.models.g2p.dataio.grapheme_pipeline
+      grapheme_encoder: *id027
+    takes: txt_cleaned
+    provides:
+    - grapheme_list
+    - grapheme_encoded_list
+    - grapheme_encoded_raw
+
+  - func: !name:speechbrain.lobes.models.g2p.dataio.add_bos_eos
+      encoder: *id027
+    takes: grapheme_encoded_list
+    provides:
+    - grapheme_encoded
+    - grapheme_len
+    - grapheme_encoded_eos
+    - grapheme_len_eos
+  - func: !name:speechbrain.lobes.models.g2p.dataio.word_emb_pipeline
+      word_emb: !ref <word_emb>
+      grapheme_encoder: !ref <grapheme_encoder>
+      use_word_emb: !ref <use_word_emb>
+    takes:
+    - txt
+    - grapheme_encoded
+    - grapheme_len
+    provides: word_emb
+
+decode_pipeline:
+  batch: true
+  output_keys:
+  - phonemes
+  steps:
+  - func: !name:speechbrain.lobes.models.g2p.dataio.beam_search_pipeline
+      beam_searcher: *id029
+    takes:
+    - char_lens
+    - encoder_out
+    provides:
+    - hyps
+    - scores
+  - func: !apply:speechbrain.utils.hparams.choice
+      value: false
+      choices:
+        true: !apply:speechbrain.lobes.models.g2p.dataio.char_map_detokenize
+          tokenizer: *id022
+          char_map: *id023
+          token_space_index: 512
+          wordwise: true
+        false: !name:speechbrain.lobes.models.g2p.dataio.phoneme_decoder_pipeline
+          phoneme_encoder: *id024
+    takes:
+    - hyps
+    provides:
+    - phonemes
+
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    model: *id014
+    ctc_lin: *id013
+

model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bf7a7b290f88de5fdd7364fa4ab249bdd94a29e6cdc742ee6f69edeae64f61
+size 128643257