msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

Merge pull request #1668 from PaddlePaddle/Jackwaterveg-patch-1

Browse Source 
[ASR] update ds2 online model
pull/1674/head
Hui Zhang 3 years ago committed by GitHub
parent 89791d7aca 82cd7015d7
commit 7ca40ff008
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 3 additions and 7 deletions
Show Stats Download Patch File Download Diff File

2
docs/source/released_model.md
Unescape View File

@ -6,7 +6,7 @@
### Speech Recognition Model ### Speech Recognition Model
Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | Example Link Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | Example Link
:-------------:| :------------:| :-----: | -----: | :-----: |:-----:| :-----: | :-----: | :-----: :-------------:| :------------:| :-----: | -----: | :-----: |:-----:| :-----: | :-----: | :-----:
[Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.080 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) [Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_ckpt_0.2.0.model.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.078 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0)
[Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_aishell_ckpt_0.1.1.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_aishell_ckpt_0.1.1.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0)
[Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0565 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) [Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0565 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1)
[Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0483 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) [Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0483 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1)

7
examples/aishell/asr0/README.md
Unescape View File

@ -173,12 +173,7 @@ bash local/data.sh --stage 2 --stop_stage 2
CUDA_VISIBLE_DEVICES= ./local/test.sh conf/deepspeech2.yaml exp/deepspeech2/checkpoints/avg_1 CUDA_VISIBLE_DEVICES= ./local/test.sh conf/deepspeech2.yaml exp/deepspeech2/checkpoints/avg_1
``` ```
The performance of the released models are shown below: The performance of the released models are shown in [this](./RESULTS.md)
| Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech |
| :----------------------------: | :-------------: | :---------: | -----: | :------------------------------------------------- | :---- | :--- | :-------------- |
| Ds2 Online Aishell ASR0 Model | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.080 | - | 151 h |
| Ds2 Offline Aishell ASR0 Model | Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers | 0.064 | - | 151 h |
## Stage 4: Static graph model Export ## Stage 4: Static graph model Export
This stage is to transform dygraph to static graph. This stage is to transform dygraph to static graph.
```bash ```bash

1
examples/aishell/asr0/RESULTS.md
Unescape View File

@ -4,6 +4,7 @@
| Model | Number of Params | Release | Config | Test set | Valid Loss | CER | | Model | Number of Params | Release | Config | Test set | Valid Loss | CER |
| --- | --- | --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- | --- | --- |
| DeepSpeech2 | 45.18M | 2.2.2 | conf/deepspeech2_online.yaml + spec aug | test | 7.708217620849609| 0.078 |
| DeepSpeech2 | 45.18M | 2.2.0 | conf/deepspeech2_online.yaml + spec aug | test | 7.994938373565674 | 0.080 | | DeepSpeech2 | 45.18M | 2.2.0 | conf/deepspeech2_online.yaml + spec aug | test | 7.994938373565674 | 0.080 |
## Deepspeech2 Non-Streaming ## Deepspeech2 Non-Streaming

Write Preview
Loading…
Cancel
Save