Skip to content

Commit 1eadb81

Browse files
author
FireRedTeam
committed
Update README.md
1 parent 5bf83d8 commit 1eadb81

File tree

4 files changed

+298
-30
lines changed

4 files changed

+298
-30
lines changed

‎LICENSE‎

Lines changed: 201 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,201 @@
1+
Apache License
2+
Version 2.0, January 2004
3+
http://www.apache.org/licenses/
4+
5+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6+
7+
1. Definitions.
8+
9+
"License" shall mean the terms and conditions for use, reproduction,
10+
and distribution as defined by Sections 1 through 9 of this document.
11+
12+
"Licensor" shall mean the copyright owner or entity authorized by
13+
the copyright owner that is granting the License.
14+
15+
"Legal Entity" shall mean the union of the acting entity and all
16+
other entities that control, are controlled by, or are under common
17+
control with that entity. For the purposes of this definition,
18+
"control" means (i) the power, direct or indirect, to cause the
19+
direction or management of such entity, whether by contract or
20+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
21+
outstanding shares, or (iii) beneficial ownership of such entity.
22+
23+
"You" (or "Your") shall mean an individual or Legal Entity
24+
exercising permissions granted by this License.
25+
26+
"Source" form shall mean the preferred form for making modifications,
27+
including but not limited to software source code, documentation
28+
source, and configuration files.
29+
30+
"Object" form shall mean any form resulting from mechanical
31+
transformation or translation of a Source form, including but
32+
not limited to compiled object code, generated documentation,
33+
and conversions to other media types.
34+
35+
"Work" shall mean the work of authorship, whether in Source or
36+
Object form, made available under the License, as indicated by a
37+
copyright notice that is included in or attached to the work
38+
(an example is provided in the Appendix below).
39+
40+
"Derivative Works" shall mean any work, whether in Source or Object
41+
form, that is based on (or derived from) the Work and for which the
42+
editorial revisions, annotations, elaborations, or other modifications
43+
represent, as a whole, an original work of authorship. For the purposes
44+
of this License, Derivative Works shall not include works that remain
45+
separable from, or merely link (or bind by name) to the interfaces of,
46+
the Work and Derivative Works thereof.
47+
48+
"Contribution" shall mean any work of authorship, including
49+
the original version of the Work and any modifications or additions
50+
to that Work or Derivative Works thereof, that is intentionally
51+
submitted to Licensor for inclusion in the Work by the copyright owner
52+
or by an individual or Legal Entity authorized to submit on behalf of
53+
the copyright owner. For the purposes of this definition, "submitted"
54+
means any form of electronic, verbal, or written communication sent
55+
to the Licensor or its representatives, including but not limited to
56+
communication on electronic mailing lists, source code control systems,
57+
and issue tracking systems that are managed by, or on behalf of, the
58+
Licensor for the purpose of discussing and improving the Work, but
59+
excluding communication that is conspicuously marked or otherwise
60+
designated in writing by the copyright owner as "Not a Contribution."
61+
62+
"Contributor" shall mean Licensor and any individual or Legal Entity
63+
on behalf of whom a Contribution has been received by Licensor and
64+
subsequently incorporated within the Work.
65+
66+
2. Grant of Copyright License. Subject to the terms and conditions of
67+
this License, each Contributor hereby grants to You a perpetual,
68+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69+
copyright license to reproduce, prepare Derivative Works of,
70+
publicly display, publicly perform, sublicense, and distribute the
71+
Work and such Derivative Works in Source or Object form.
72+
73+
3. Grant of Patent License. Subject to the terms and conditions of
74+
this License, each Contributor hereby grants to You a perpetual,
75+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76+
(except as stated in this section) patent license to make, have made,
77+
use, offer to sell, sell, import, and otherwise transfer the Work,
78+
where such license applies only to those patent claims licensable
79+
by such Contributor that are necessarily infringed by their
80+
Contribution(s) alone or by combination of their Contribution(s)
81+
with the Work to which such Contribution(s) was submitted. If You
82+
institute patent litigation against any entity (including a
83+
cross-claim or counterclaim in a lawsuit) alleging that the Work
84+
or a Contribution incorporated within the Work constitutes direct
85+
or contributory patent infringement, then any patent licenses
86+
granted to You under this License for that Work shall terminate
87+
as of the date such litigation is filed.
88+
89+
4. Redistribution. You may reproduce and distribute copies of the
90+
Work or Derivative Works thereof in any medium, with or without
91+
modifications, and in Source or Object form, provided that You
92+
meet the following conditions:
93+
94+
(a) You must give any other recipients of the Work or
95+
Derivative Works a copy of this License; and
96+
97+
(b) You must cause any modified files to carry prominent notices
98+
stating that You changed the files; and
99+
100+
(c) You must retain, in the Source form of any Derivative Works
101+
that You distribute, all copyright, patent, trademark, and
102+
attribution notices from the Source form of the Work,
103+
excluding those notices that do not pertain to any part of
104+
the Derivative Works; and
105+
106+
(d) If the Work includes a "NOTICE" text file as part of its
107+
distribution, then any Derivative Works that You distribute must
108+
include a readable copy of the attribution notices contained
109+
within such NOTICE file, excluding those notices that do not
110+
pertain to any part of the Derivative Works, in at least one
111+
of the following places: within a NOTICE text file distributed
112+
as part of the Derivative Works; within the Source form or
113+
documentation, if provided along with the Derivative Works; or,
114+
within a display generated by the Derivative Works, if and
115+
wherever such third-party notices normally appear. The contents
116+
of the NOTICE file are for informational purposes only and
117+
do not modify the License. You may add Your own attribution
118+
notices within Derivative Works that You distribute, alongside
119+
or as an addendum to the NOTICE text from the Work, provided
120+
that such additional attribution notices cannot be construed
121+
as modifying the License.
122+
123+
You may add Your own copyright statement to Your modifications and
124+
may provide additional or different license terms and conditions
125+
for use, reproduction, or distribution of Your modifications, or
126+
for any such Derivative Works as a whole, provided Your use,
127+
reproduction, and distribution of the Work otherwise complies with
128+
the conditions stated in this License.
129+
130+
5. Submission of Contributions. Unless You explicitly state otherwise,
131+
any Contribution intentionally submitted for inclusion in the Work
132+
by You to the Licensor shall be under the terms and conditions of
133+
this License, without any additional terms or conditions.
134+
Notwithstanding the above, nothing herein shall supersede or modify
135+
the terms of any separate license agreement you may have executed
136+
with Licensor regarding such Contributions.
137+
138+
6. Trademarks. This License does not grant permission to use the trade
139+
names, trademarks, service marks, or product names of the Licensor,
140+
except as required for reasonable and customary use in describing the
141+
origin of the Work and reproducing the content of the NOTICE file.
142+
143+
7. Disclaimer of Warranty. Unless required by applicable law or
144+
agreed to in writing, Licensor provides the Work (and each
145+
Contributor provides its Contributions) on an "AS IS" BASIS,
146+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147+
implied, including, without limitation, any warranties or conditions
148+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149+
PARTICULAR PURPOSE. You are solely responsible for determining the
150+
appropriateness of using or redistributing the Work and assume any
151+
risks associated with Your exercise of permissions under this License.
152+
153+
8. Limitation of Liability. In no event and under no legal theory,
154+
whether in tort (including negligence), contract, or otherwise,
155+
unless required by applicable law (such as deliberate and grossly
156+
negligent acts) or agreed to in writing, shall any Contributor be
157+
liable to You for damages, including any direct, indirect, special,
158+
incidental, or consequential damages of any character arising as a
159+
result of this License or out of the use or inability to use the
160+
Work (including but not limited to damages for loss of goodwill,
161+
work stoppage, computer failure or malfunction, or any and all
162+
other commercial damages or losses), even if such Contributor
163+
has been advised of the possibility of such damages.
164+
165+
9. Accepting Warranty or Additional Liability. While redistributing
166+
the Work or Derivative Works thereof, You may choose to offer,
167+
and charge a fee for, acceptance of support, warranty, indemnity,
168+
or other liability obligations and/or rights consistent with this
169+
License. However, in accepting such obligations, You may act only
170+
on Your own behalf and on Your sole responsibility, not on behalf
171+
of any other Contributor, and only if You agree to indemnify,
172+
defend, and hold each Contributor harmless for any liability
173+
incurred by, or claims asserted against, such Contributor by reason
174+
of your accepting any such warranty or additional liability.
175+
176+
END OF TERMS AND CONDITIONS
177+
178+
APPENDIX: How to apply the Apache License to your work.
179+
180+
To apply the Apache License to your work, attach the following
181+
boilerplate notice, with the fields enclosed by brackets "[]"
182+
replaced with your own identifying information. (Don't include
183+
the brackets!) The text should be enclosed in the appropriate
184+
comment syntax for the file format. We also recommend that a
185+
file or class name and description of purpose be included on the
186+
same "printed page" as the copyright notice for easier
187+
identification within third-party archives.
188+
189+
Copyright [yyyy] [name of copyright owner]
190+
191+
Licensed under the Apache License, Version 2.0 (the "License");
192+
you may not use this file except in compliance with the License.
193+
You may obtain a copy of the License at
194+
195+
http://www.apache.org/licenses/LICENSE-2.0
196+
197+
Unless required by applicable law or agreed to in writing, software
198+
distributed under the License is distributed on an "AS IS" BASIS,
199+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200+
See the License for the specific language governing permissions and
201+
limitations under the License.

‎README.md‎

Lines changed: 94 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -1,43 +1,89 @@
1-
# FireRedASR
1+
<div align="center">
2+
<h1>FireRedASR: Open-Source Industrial-Grade
3+
<br>
4+
Automatic Speech Recognition Models</h1>
25

3-
[[Blog]](https://fireredteam.github.io/demos/firered_asr/)
4-
[[Paper]]()
6+
</div>
7+
8+
[[Paper]](https://arxiv.org/pdf/2501.14350)
59
[[Model]](https://huggingface.co/fireredteam)
10+
[[Blog]](https://fireredteam.github.io/demos/firered_asr/)
11+
12+
FireRedASR is a family of open-source industrial-grade automatic speech recognition (ASR) models supporting Mandarin, Chinese dialects and English, achieving a new state-of-the-art (SOTA) on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
13+
14+
15+
## 🔥 News
16+
- [2025/02/17] We release [FireRedASR-LLM-L](https://huggingface.co/fireredteam/FireRedASR-LLM-L/tree/main) model weights.
17+
- [2025/01/24] We release [technical report](https://arxiv.org/pdf/2501.14350), [blog](https://fireredteam.github.io/demos/firered_asr/), and [FireRedASR-AED-L](https://huggingface.co/fireredteam/FireRedASR-AED-L/tree/main) model weights.
18+
19+
20+
## Method
621

7-
FireRedASR, a family of large-scale automatic speech recognition (ASR) models for Mandarin, designed to meet diverse requirements in superior performance and optimal efficiency across various applications. FireRedASR comprises two variants:
22+
FireRedASR is designed to meet diverse requirements in superior performance and optimal efficiency across various applications. It comprises two variants:
823
- FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities.
924
- FireRedASR-AED: Designed to balance high performance and computational efficiency and to serve as an effective speech representation module in LLM-based speech models. It utilizes an Attention-based Encoder-Decoder (AED) architecture.
1025

1126
![Model](/assets/FireRedASR_model.png)
1227

1328

14-
## News
15-
- [2025/01/24] 🔥 We release [techincal report]()(under review at arXiv), [blog](https://fireredteam.github.io/demos/firered_asr/), and [FireRedASR-AED-L](https://huggingface.co/fireredteam/FireRedASR-AED-L/tree/main) model weights.
16-
- [WIP] We plan to release FireRedASR-LLM-L after the Spring Festival.
29+
## Evaluation
30+
Results are reported in Character Error Rate (CER%) for Chinese and Word Error Rate (WER%) for English.
31+
32+
### Evaluation on Public Mandarin ASR Benchmarks
33+
| Model | #Params | aishell1 | aishell2 | ws\_net | ws\_meeting | Average-4 |
34+
|:----------------:|:-------:|:--------:|:--------:|:--------:|:-----------:|:---------:|
35+
| FireRedASR-LLM | 8.3B | 0.76 | 2.15 | 4.60 | 4.67 | 3.05 |
36+
| FireRedASR-AED | 1.1B | 0.55 | 2.52 | 4.88 | 4.76 | 3.18 |
37+
| Seed-ASR | 12B+ | 0.68 | 2.27 | 4.66 | 5.69 | 3.33 |
38+
| Qwen-Audio | 8.4B | 1.30 | 3.10 | 9.50 | 10.87 | 6.19 |
39+
| SenseVoice-L | 1.6B | 2.09 | 3.04 | 6.01 | 6.73 | 4.47 |
40+
| Whisper-Large-v3 | 1.6B | 5.14 | 4.96 | 10.48 | 18.87 | 9.86 |
41+
| Paraformer-Large | 0.2B | 1.68 | 2.85 | 6.74 | 6.97 | 4.56 |
42+
43+
`ws` means WenetSpeech.
44+
45+
### Evaluation on Public Chinese Dialect and English ASR Benchmarks
46+
|Test Set | KeSpeech | LibriSpeech test-clean | LibriSpeech test-other |
47+
| :------------:| :------: | :--------------------: | :----------------------:|
48+
|FireRedASR-LLM | 3.56 | 1.73 | 3.67 |
49+
|FireRedASR-AED | 4.48 | 1.93 | 4.44 |
50+
|Previous SOTA Results | 6.70 | 1.82 | 3.50 |
51+
52+
53+
## Usage
54+
Download model files from [huggingface](https://huggingface.co/fireredteam) and place them in the folder `pretrained_models`.
55+
56+
If you want to use `FireRedASR-LLM-L`, you also need to download [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) and place it in the folder `pretrained_models`. Then, go to folder `FireRedASR-LLM-L` and run `$ ln -s ../Qwen2-7B-Instruct`
1757

18-
## Setup
1958

59+
### Setup
60+
Create a Python environment and install dependencies
2061
```bash
2162
$ git clone https://github.com/FireRedTeam/FireRedASR.git
2263
$ conda create --name fireredasr python=3.10
2364
$ pip install -r requirements.txt
2465
```
2566

26-
## Usage
27-
Download model files from [huggingface](https://huggingface.co/fireredteam) and place them in the folder `pretrained_models`
67+
Set up Linux PATH and PYTHONPATH
68+
```
69+
$ export PATH=$PWD/fireredasr/:$PWD/fireredasr/utils/:$PATH
70+
$ export PYTHONPATH=$PWD/:$PYTHONPATH
71+
```
72+
73+
Convert audio to 16kHz 16-bit PCM format
74+
```
75+
ffmpeg -i input_audio -ar 16000 -ac 1 -acodec pcm_s16le -f wav output.wav
76+
```
2877

2978
### Quick Start
3079
```bash
31-
$ cd examples/
80+
$ cd examples
3281
$ bash inference_fireredasr_aed.sh
3382
$ bash inference_fireredasr_llm.sh
3483
```
3584

36-
### Commond-line Usage
85+
### Command-line Usage
3786
```bash
38-
# Setup PATH & PYTHONPATH
39-
$ export PATH=$PWD/fireredasr/:$PWD/fireredasr/utils/:$PATH
40-
$ export PYTHONPATH=$PWD/:$PYTHONPATH
4187
$ speech2text.py --help
4288
$ speech2text.py --wav_path examples/wav/BAC009S0764W0121.wav --asr_type "aed" --model_dir pretrained_models/FireRedASR-AED-L
4389
$ speech2text.py --wav_path examples/wav/BAC009S0764W0121.wav --asr_type "llm" --model_dir pretrained_models/FireRedASR-LLM-L
@@ -56,13 +102,13 @@ results = model.transcribe(
56102
batch_uttid,
57103
batch_wav_path,
58104
{
59-
"use_gpu": 1,
60-
"beam_size": 3,
61-
"nbest": 1,
62-
"decode_max_len": 0,
63-
"softmax_smoothing": 1.0,
64-
"aed_length_penalty": 0.0,
65-
"eos_penalty": 1.0
105+
"use_gpu": 1,
106+
"beam_size": 3,
107+
"nbest": 1,
108+
"decode_max_len": 0,
109+
"softmax_smoothing": 1.25,
110+
"aed_length_penalty": 0.6,
111+
"eos_penalty": 1.0
66112
}
67113
)
68114
print(results)
@@ -74,22 +120,41 @@ results = model.transcribe(
74120
batch_uttid,
75121
batch_wav_path,
76122
{
77-
"use_gpu": 1,
78-
"beam_size": 3,
79-
"decode_max_len": 0,
80-
"decode_min_len": 0,
81-
"repetition_penalty": 1.0,
82-
"llm_length_penalty": 0.0,
83-
"temperature": 1.0
123+
"use_gpu": 1,
124+
"beam_size": 3,
125+
"decode_max_len": 0,
126+
"decode_min_len": 0,
127+
"repetition_penalty": 3.0,
128+
"llm_length_penalty": 1.0,
129+
"temperature": 1.0
84130
}
85131
)
86132
print(results)
87133
```
88134

135+
## Usage Tips
136+
### Batch Beam Search
137+
- When performing batch beam search with FireRedASR-LLM, please ensure that the input lengths of the utterances are similar. If there are significant differences in utterance lengths, shorter utterances may experience repetition issues. You can either sort your dataset by length or set `batch_size` to 1 to avoid the repetition issue.
138+
139+
### Input Length Limitations
140+
- FireRedASR-AED supports audio input up to 60s. Input longer than 60s may cause hallucination issues, and input exceeding 200s will trigger positional encoding errors.
141+
- FireRedASR-LLM supports audio input up to 30s. The behavior for longer input is currently unknown.
142+
89143

90144
## Acknowledgements
91145
Thanks to the following open-source works:
92146
- [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)
93147
- [icefall/ASR_LLM](https://github.com/k2-fsa/icefall/tree/master/egs/speech_llm/ASR_LLM)
94148
- [WeNet](https://github.com/wenet-e2e/wenet)
95149
- [Speech-Transformer](https://github.com/kaituoxu/Speech-Transformer)
150+
151+
152+
## Citation
153+
```bibtex
154+
@article{xu2025fireredasr,
155+
title={FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration},
156+
author={Xu, Kai-Tuo and Xie, Feng-Long and Tang, Xu and Hu, Yao},
157+
journal={arXiv preprint arXiv:2501.14350},
158+
year={2025}
159+
}
160+
```

‎fireredasr/models/fireredasr_llm.py‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,8 @@ def load_encoder(cls, model_path):
2020
assert os.path.exists(model_path)
2121
package = torch.load(model_path, map_location=lambda storage, loc: storage)
2222
model = FireRedAsrAed.from_args(package["args"])
23-
model.load_state_dict(package["model_state_dict"], strict=False)
23+
if "model_state_dict" in package:
24+
model.load_state_dict(package["model_state_dict"], strict=False)
2425
encoder = model.encoder
2526
encoder_dim = encoder.odim
2627
return encoder, encoder_dim

‎requirements.txt‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,5 +3,6 @@ kaldiio>=2.18.0
33
kaldi_native_fbank>=1.15
44
numpy>=1.26.1
55
peft>=0.13.2
6+
sentencepiece
67
torch>=2.0.0
78
transformers>=4.46.3

0 commit comments

Comments
 (0)