Add model weights and hyparams

README.md

@@ -0,0 +1,108 @@
+---
+language: "kr"
+thumbnail:
+tags:
+- ASR
+- CTC
+- Attention
+- Conformer
+- pytorch
+- speechbrain
+license: "apache-2.0"
+datasets:
+- ksponspeech
+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/>
+
+# Conformer for KsponSpeech (with Transformer LM)
+
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end system pretrained on KsponSpeech (Kr) 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 | eval clean CER | eval other CER | GPUs |
+|:-------------:|:--------------:|:--------------:|:--------:|
+| 09-05-21 | 7.86 | 8.93 | 6xA100 80GB |
+
+## Pipeline description
+
+This ASR system is composed of 3 different but linked blocks:
+- Tokenizer (unigram) that transforms words into subword units and trained with
+the train transcriptions of KsponSpeech.
+- Neural language model (Transformer LM) trained on the train transcriptions of KsponSpeech
+- Acoustic model made of a conformer encoder and a joint decoder with CTC +
+transformer. Hence, the decoding also incorporates the CTC probabilities.
+## Install SpeechBrain
+First of all, please install SpeechBrain with the following command:
+```
+!pip install git+https://github.com/speechbrain/speechbrain.git@develop
+```
+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 Korean)
+```python
+from speechbrain.pretrained import EncoderDecoderASR
+asr_model = EncoderDecoderASR.from_hparams(source="dave-rtzr/ksponspeech-conformer-medium", savedir="pretrained_models/ksponspeech-conformer-medium",  run_opts={"device":"cuda"})
+asr_model.transcribe_file("dave-rtzr/ksponspeech-conformer-medium/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/10N98aGoeLGfh6Hu6xOCH5BbjVTVYgCyB?usp=sharing) on using the pretrained model
+
+### Training
+
+The model was trained with SpeechBrain (Commit hash: 'fd9826c').
+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 .
+```
+3. Run Training:
+```bash
+cd recipes/KsponSpeech/ASR/transformer
+python train.py hparams/conformer_medium.yaml --data_folder=your_data_folder
+```
+You can find our training results (models, logs, etc) at the subdirectories.
+
+### 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}
+}
+```

asr.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893a5fb84a67315a954d7645fd3b5f96cee806531f538e0073f6dcdf17dcf7c3
+size 183510489

hyperparams.yaml

@@ -0,0 +1,151 @@
+# ############################################################################
+# Model: E2E ASR with Transformer
+# Encoder: Conformer Encoder
+# Decoder: Transformer Decoder + (CTC/ATT joint) beamsearch + TransformerLM
+# Tokens: unigram
+# losses: CTC + KLdiv (Label Smoothing loss)
+# Training: KsponSpeech 965.2h
+# Authors: Dongwon Kim, Dongwoo Kim 
+# ############################################################################
+# Seed needs to be set at top of yaml, before objects with parameters are made
+
+# Feature parameters
+sample_rate: 16000
+n_fft: 400
+n_mels: 80
+
+####################### Model parameters ###########################
+# Transformer
+d_model: 256
+nhead: 4
+num_encoder_layers: 12
+num_decoder_layers: 6
+d_ffn: 2048
+transformer_dropout: 0.0
+activation: !name:torch.nn.GELU
+output_neurons: 5000
+vocab_size: 5000
+
+# Outputs
+blank_index: 0
+label_smoothing: 0.1
+pad_index: 0
+bos_index: 1
+eos_index: 2
+unk_index: 0
+
+# Decoding parameters
+min_decode_ratio: 0.0
+max_decode_ratio: 1.0
+valid_search_interval: 10
+valid_beam_size: 10
+test_beam_size: 60
+lm_weight: 0.60
+ctc_weight_decode: 0.40
+
+############################## models ################################
+
+normalizer: !new:speechbrain.processing.features.InputNormalization
+    norm_type: global
+
+CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd
+    input_shape: (8, 10, 80)
+    num_blocks: 2
+    num_layers_per_block: 1
+    out_channels: (64, 32)
+    kernel_sizes: (3, 3)
+    strides: (2, 2)
+    residuals: (False, False)
+
+Transformer: !new:speechbrain.lobes.models.transformer.TransformerASR.TransformerASR # yamllint disable-line rule:line-length
+    input_size: 640
+    tgt_vocab: !ref <output_neurons>
+    d_model: !ref <d_model>
+    nhead: !ref <nhead>
+    num_encoder_layers: !ref <num_encoder_layers>
+    num_decoder_layers: !ref <num_decoder_layers>
+    d_ffn: !ref <d_ffn>
+    dropout: !ref <transformer_dropout>
+    activation: !ref <activation>
+    encoder_module: conformer
+    attention_type: RelPosMHAXL
+    normalize_before: True
+    causal: False
+
+# NB: It has to match the pre-trained TransformerLM!!
+lm_model: !new:speechbrain.lobes.models.transformer.TransformerLM.TransformerLM # yamllint disable-line rule:line-length
+    vocab: !ref <output_neurons>
+    d_model: 768
+    nhead: 12
+    num_encoder_layers: 12
+    num_decoder_layers: 0
+    d_ffn: 3072
+    dropout: 0.0
+    activation: !name:torch.nn.GELU
+    normalize_before: False
+
+tokenizer: !new:sentencepiece.SentencePieceProcessor
+
+ctc_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <d_model>
+    n_neurons: !ref <output_neurons>
+
+seq_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <d_model>
+    n_neurons: !ref <output_neurons>
+
+decoder: !new:speechbrain.decoders.S2STransformerBeamSearch
+    modules: [!ref <Transformer>, !ref <seq_lin>, !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 <test_beam_size>
+    ctc_weight: !ref <ctc_weight_decode>
+    lm_weight: !ref <lm_weight>
+    lm_modules: !ref <lm_model>
+    temperature: 1.15
+    temperature_lm: 1.15
+    using_eos_threshold: False
+    length_normalization: True
+
+Tencoder: !new:speechbrain.lobes.models.transformer.TransformerASR.EncoderWrapper
+    transformer: !ref <Transformer>
+
+encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
+    input_shape: [null, null, !ref <n_mels>]
+    compute_features: !ref <compute_features>
+    normalize: !ref <normalizer>
+    cnn: !ref <CNN>
+    transformer_encoder: !ref <Tencoder>
+
+asr_model: !new:torch.nn.ModuleList
+    - [!ref <normalizer>, !ref <CNN>, !ref <Transformer>, !ref <seq_lin>, !ref <ctc_lin>]
+
+log_softmax: !new:torch.nn.LogSoftmax
+    dim: -1
+
+
+compute_features: !new:speechbrain.lobes.features.Fbank
+    sample_rate: !ref <sample_rate>
+    n_fft: !ref <n_fft>
+    n_mels: !ref <n_mels>
+
+modules:
+   compute_features: !ref <compute_features>
+   normalizer: !ref <normalizer>
+   pre_transformer: !ref <CNN>
+   transformer: !ref <Transformer>
+   asr_model: !ref <asr_model>
+   lm_model: !ref <lm_model>
+   encoder: !ref <encoder>
+   decoder: !ref <decoder>
+# The pretrainer allows a mapping between pretrained files and instances that
+# are declared in the yaml.
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+   loadables:
+      normalizer: !ref <normalizer>
+      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:ee4a5a5d9ce11e24dcea93f24a241528b9b376798be6478c70fb279736515110
+size 381074814

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4866d96b29f5c97526c7469aa6f58cd50aeb9865b457daf599f0f42e5827be9
+size 1783

tokenizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e095c023a42b6bd25352512597a245db9bf9126ce6bf64082bd41d0a196b220
+size 313899