whisper-large-v3
Automatic speech recognition model, used with transformers.
- 6.8k
- 3.2M
- apache-2.0
- 3 y ago
Automatic speech recognition model, used with transformers.
Model FireRedTeam/FireRedPunc, read from Hugging Face 1 min ago.
FireRedTeam/FireRedPunc is a model on Hugging Face by FireRedTeam. Automatic speech recognition model, used with transformers. It declares the apache-2.0 license on Hugging Face. It has 20 likes and last changed on 2026-03-13. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from Hugging Face on 2026-11-22.
The author's own card, shown from Hugging Face. Take My Repo does not keep a copy.
[Code] [Paper] [Model🤗] [Model🤖] [Demo]
FireRedASR2S is a state-of-the-art (SOTA), industrial-grade, all-in-one ASR system with ASR, VAD, LID, and Punc modules. All modules achieve SOTA performance:
2S: 2nd-generation FireRedASR, now expanded to an all-in-one ASR System
| Model | Supported Languages & Dialects | Download |
|---|---|---|
| FireRedASR2-LLM | Chinese (Mandarin and 20+ dialects/accents*), English, Code-Switching | 🤗 | 🤖 |
| FireRedASR2-AED | Chinese (Mandarin and 20+ dialects/accents*), English, Code-Switching | 🤗 | 🤖 |
| FireRedVAD | 100+ languages, 20+ Chinese dialects/accents* | 🤗 | 🤖 |
| FireRedLID | 100+ languages, 20+ Chinese dialects/accents* | 🤗 | 🤖 |
| FireRedPunc | Chinese, English | 🤗 | 🤖 |
*Supported Chinese dialects/accents: Cantonese (Hong Kong & Guangdong), Sichuan, Shanghai, Wu, Minnan, Anhui, Fujian, Gansu, Guizhou, Hebei, Henan, Hubei, Hunan, Jiangxi, Liaoning, Ningxia, Shaanxi, Shanxi, Shandong, Tianjin, Yunnan, etc.

FireRedASR2 builds upon FireRedASR with improved accuracy, designed to meet diverse requirements in superior performance and optimal efficiency across various applications. It comprises two variants:

$ conda create --name fireredasr2s python=3.10
$ conda activate fireredasr2s
$ git clone https://github.com/FireRedTeam/FireRedASR2S.git
$ cd FireRedASR2S # or fireredasr2s
$ pip install -r requirements.txt
$ export PATH=$PWD/fireredasr2s/:$PATH
$ export PYTHONPATH=$PWD/:$PYTHONPATH
# Download via ModelScope (recommended for users in China)
pip install -U modelscope
modelscope download --model xukaituo/FireRedASR2-AED --local_dir ./pretrained_models/FireRedASR2-AED
modelscope download --model xukaituo/FireRedVAD --local_dir ./pretrained_models/FireRedVAD
modelscope download --model xukaituo/FireRedLID --local_dir ./pretrained_models/FireRedLID
modelscope download --model xukaituo/FireRedPunc --local_dir ./pretrained_models/FireRedPunc
modelscope download --model xukaituo/FireRedASR2-LLM --local_dir ./pretrained_models/FireRedASR2-LLM
# Download via Hugging Face
pip install -U "huggingface_hub[cli]"
huggingface-cli download FireRedTeam/FireRedASR2-AED --local-dir ./pretrained_models/FireRedASR2-AED
huggingface-cli download FireRedTeam/FireRedVAD --local-dir ./pretrained_models/FireRedVAD
huggingface-cli download FireRedTeam/FireRedLID --local-dir ./pretrained_models/FireRedLID
huggingface-cli download FireRedTeam/FireRedPunc --local-dir ./pretrained_models/FireRedPunc
huggingface-cli download FireRedTeam/FireRedASR2-LLM --local-dir ./pretrained_models/FireRedASR2-LLM
$ ffmpeg -i <input_audio_path> -ar 16000 -ac 1 -acodec pcm_s16le -f wav <output_wav_path>
$ cd examples_infer/asr_system
$ bash inference_asr_system.sh
$ fireredasr2s-cli --help
$ fireredasr2s-cli --wav_paths "assets/hello_zh.wav" "assets/hello_en.wav" --outdir output
$ cat output/result.jsonl
# {"uttid": "hello_zh", "text": "你好世界。", "sentences": [{"start_ms": 310, "end_ms": 1840, "text": "你好世界。", "asr_confidence": 0.875, "lang": "zh mandarin", "lang_confidence": 0.999}], "vad_segments_ms": [[310, 1840]], "dur_s": 2.32, "words": [{"start_ms": 490, "end_ms": 690, "text": "你"}, {"start_ms": 690, "end_ms": 1090, "text": "好"}, {"start_ms": 1090, "end_ms": 1330, "text": "世"}, {"start_ms": 1330, "end_ms": 1795, "text": "界"}], "wav_path": "assets/hello_zh.wav"}
# {"uttid": "hello_en", "text": "Hello speech.", "sentences": [{"start_ms": 120, "end_ms": 1840, "text": "Hello speech.", "asr_confidence": 0.833, "lang": "en", "lang_confidence": 0.998}], "vad_segments_ms": [[120, 1840]], "dur_s": 2.24, "words": [{"start_ms": 340, "end_ms": 1020, "text": "hello"}, {"start_ms": 1020, "end_ms": 1666, "text": "speech"}], "wav_path": "assets/hello_en.wav"}
from fireredasr2s import FireRedAsr2System, FireRedAsr2SystemConfig
asr_system_config = FireRedAsr2SystemConfig() # Use default config
asr_system = FireRedAsr2System(asr_system_config)
result = asr_system.process("assets/hello_zh.wav")
print(result)
# {'uttid': 'tmpid', 'text': '你好世界。', 'sentences': [{'start_ms': 440, 'end_ms': 1820, 'text': '你好世界。', 'asr_confidence': 0.868, 'lang': 'zh mandarin', 'lang_confidence': 0.999}], 'vad_segments_ms': [(440, 1820)], 'dur_s': 2.32, 'words': [], 'wav_path': 'assets/hello_zh.wav'}
result = asr_system.process("assets/hello_en.wav")
print(result)
# {'uttid': 'tmpid', 'text': 'Hello speech.', 'sentences': [{'start_ms': 260, 'end_ms': 1820, 'text': 'Hello speech.', 'asr_confidence': 0.933, 'lang': 'en', 'lang_confidence': 0.993}], 'vad_segments_ms': [(260, 1820)], 'dur_s': 2.24, 'words': [], 'wav_path': 'assets/hello_en.wav'}
The four components under fireredasr2s, i.e. fireredasr2, fireredvad, fireredlid, and fireredpunc are self-contained and designed to work as a standalone modules. You can use any of them independently without depending on the others. FireRedVAD and FireRedLID will also be open-sourced as standalone libraries in separate repositories.
# ASR
$ cd examples_infer/asr
$ bash inference_asr_aed.sh
$ bash inference_asr_llm.sh
# VAD & mVAD (mVAD=Audio Event Detection, AED)
$ cd examples_infer/vad
$ bash inference_vad.sh
$ bash inference_streamvad.sh
$ bash inference_aed.sh
# LID
$ cd examples_infer/lid
$ bash inference_lid.sh
# Punc
$ cd examples_infer/punc
$ bash inference_punc.sh
# Serving FireRedASR2-LLM with latest vLLM for the highest performance.
# For more details, see https://github.com/vllm-project/vllm/pull/35727.
$ vllm serve allendou/FireRedASR2-LLM-vllm -tp=2 --dtype=float32
$ python3 examples/online_serving/openai_transcription_client.py --repetition_penalty=1.0 --audio_path=/root/hello_zh.wav
Set up PYTHONPATH first: export PYTHONPATH=$PWD/:$PYTHONPATH
from fireredasr2s.fireredasr2 import FireRedAsr2, FireRedAsr2Config
batch_uttid = ["hello_zh", "hello_en"]
batch_wav_path = ["assets/hello_zh.wav", "assets/hello_en.wav"]
# FireRedASR2-AED
asr_config = FireRedAsr2Config(
use_gpu=True,
use_half=False,
beam_size=3,
nbest=1,
decode_max_len=0,
softmax_smoothing=1.25,
aed_length_penalty=0.6,
eos_penalty=1.0,
return_timestamp=True
)
model = FireRedAsr2.from_pretrained("aed", "pretrained_models/FireRedASR2-AED", asr_config)
results = model.transcribe(batch_uttid, batch_wav_path)
print(results)
# [{'uttid': 'hello_zh', 'text': '你好世界', 'confidence': 0.971, 'dur_s': 2.32, 'rtf': '0.0870', 'wav': 'assets/hello_zh.wav', 'timestamp': [('你', 0.42, 0.66), ('好', 0.66, 1.1), ('世', 1.1, 1.34), ('界', 1.34, 2.039)]}, {'uttid': 'hello_en', 'text': 'hello speech', 'confidence': 0.943, 'dur_s': 2.24, 'rtf': '0.0870', 'wav': 'assets/hello_en.wav', 'timestamp': [('hello', 0.34, 0.98), ('speech', 0.98, 1.766)]}]
# FireRedASR2-LLM
asr_config = FireRedAsr2Config(
use_gpu=True,
decode_min_len=0,
repetition_penalty=1.0,
llm_length_penalty=0.0,
temperature=1.0
)
model = FireRedAsr2.from_pretrained("llm", "pretrained_models/FireRedASR2-LLM", asr_config)
results = model.transcribe(batch_uttid, batch_wav_path)
print(results)
# [{'uttid': 'hello_zh', 'text': '你好世界', 'rtf': '0.0681', 'wav': 'assets/hello_zh.wav'}, {'uttid': 'hello_en', 'text': 'hello speech', 'rtf': '0.0681', 'wav': 'assets/hello_en.wav'}]
from fireredasr2s.fireredvad import FireRedVad, FireRedVadConfig
vad_config = FireRedVadConfig(
use_gpu=False,
smooth_window_size=5,
speech_threshold=0.4,
min_speech_frame=20,
max_speech_frame=2000,
min_silence_frame=20,
merge_silence_frame=0,
extend_speech_frame=0,
chunk_max_frame=30000)
vad = FireRedVad.from_pretrained("pretrained_models/FireRedVAD/VAD", vad_config)
result, probs = vad.detect("assets/hello_zh.wav")
print(result)
# {'dur': 2.32, 'timestamps': [(0.44, 1.82)], 'wav_path': 'assets/hello_zh.wav'}
from fireredasr2s.fireredvad import FireRedStreamVad, FireRedStreamVadConfig
vad_config=FireRedStreamVadConfig(
use_gpu=False,
smooth_window_size=5,
speech_threshold=0.4,
pad_start_frame=5,
min_speech_frame=8,
max_speech_frame=2000,
min_silence_frame=20,
chunk_max_frame=30000)
stream_vad = FireRedStreamVad.from_pretrained("pretrained_models/FireRedVAD/Stream-VAD", vad_config)
frame_results, result = stream_vad.detect_full("assets/hello_zh.wav")
print(result)
# {'dur': 2.32, 'timestamps': [(0.46, 1.84)], 'wav_path': 'assets/hello_zh.wav'}
from fireredasr2s.fireredvad import FireRedAed, FireRedAedConfig
aed_config=FireRedAedConfig(
use_gpu=False,
smooth_window_size=5,
speech_threshold=0.4,
singing_threshold=0.5,
music_threshold=0.5,
min_event_frame=20,
max_event_frame=2000,
min_silence_frame=20,
merge_silence_frame=0,
extend_speech_frame=0,
chunk_max_frame=30000)
aed = FireRedAed.from_pretrained("pretrained_models/FireRedVAD/AED", aed_config)
result, probs = aed.detect("assets/event.wav")
print(result)
# {'dur': 22.016, 'event2timestamps': {'speech': [(0.4, 3.56), (3.66, 9.08), (9.27, 9.77), (10.78, 21.76)], 'singing': [(1.79, 19.96), (19.97, 22.016)], 'music': [(0.09, 12.32), (12.33, 22.016)]}, 'event2ratio': {'speech': 0.848, 'singing': 0.905, 'music': 0.991}, 'wav_path': 'assets/event.wav'}
from fireredasr2s.fireredlid import FireRedLid, FireRedLidConfig
batch_uttid = ["hello_zh", "hello_en"]
batch_wav_path = ["assets/hello_zh.wav", "assets/hello_en.wav"]
config = FireRedLidConfig(use_gpu=True, use_half=False)
model = FireRedLid.from_pretrained("pretrained_models/FireRedLID", config)
results = model.process(batch_uttid, batch_wav_path)
print(results)
# [{'uttid': 'hello_zh', 'lang': 'zh mandarin', 'confidence': 0.996, 'dur_s': 2.32, 'rtf': '0.0741', 'wav': 'assets/hello_zh.wav'}, {'uttid': 'hello_en', 'lang': 'en', 'confidence': 0.996, 'dur_s': 2.24, 'rtf': '0.0741', 'wav': 'assets/hello_en.wav'}]
from fireredasr2s.fireredpunc.punc import FireRedPunc, FireRedPuncConfig
config = FireRedPuncConfig(use_gpu=True)
model = FireRedPunc.from_pretrained("pretrained_models/FireRedPunc", config)
batch_text = ["你好世界", "Hello world"]
results = model.process(batch_text)
print(results)
# [{'punc_text': '你好世界。', 'origin_text': '你好世界'}, {'punc_text': 'Hello world!', 'origin_text': 'Hello world'}]
from fireredasr2s.fireredasr2 import FireRedAsr2Config
from fireredasr2s.fireredlid import FireRedLidConfig
from fireredasr2s.fireredpunc import FireRedPuncConfig
from fireredasr2s.fireredvad import FireRedVadConfig
from fireredasr2s import FireRedAsr2System, FireRedAsr2SystemConfig
vad_config = FireRedVadConfig(
use_gpu=False,
smooth_window_size=5,
speech_threshold=0.4,
min_speech_frame=20,
max_speech_frame=2000,
min_silence_frame=20,
merge_silence_frame=0,
extend_speech_frame=0,
chunk_max_frame=30000
)
lid_config = FireRedLidConfig(use_gpu=True, use_half=False)
asr_config = FireRedAsr2Config(
use_gpu=True,
use_half=False,
beam_size=3,
nbest=1,
decode_max_len=0,
softmax_smoothing=1.25,
aed_length_penalty=0.6,
eos_penalty=1.0,
return_timestamp=True
)
punc_config = FireRedPuncConfig(use_gpu=True)
asr_system_config = FireRedAsr2SystemConfig(
"pretrained_models/FireRedVAD/VAD",
"pretrained_models/FireRedLID",
"aed", "pretrained_models/FireRedASR2-AED",
"pretrained_models/FireRedPunc",
vad_config, lid_config, asr_config, punc_config,
enable_vad=1, enable_lid=1, enable_punc=1
)
asr_system = FireRedAsr2System(asr_system_config)
batch_uttid = ["hello_zh", "hello_en"]
batch_wav_path = ["assets/hello_zh.wav", "assets/hello_en.wav"]
for wav_path, uttid in zip(batch_wav_path, batch_uttid):
result = asr_system.process(wav_path, uttid)
print(result)
# {'uttid': 'hello_zh', 'text': '你好世界。', 'sentences': [{'start_ms': 440, 'end_ms': 1820, 'text': '你好世界。', 'asr_confidence': 0.868, 'lang': 'zh mandarin', 'lang_confidence': 0.999}], 'vad_segments_ms': [(440, 1820)], 'dur_s': 2.32, 'words': [{'start_ms': 540, 'end_ms': 700, 'text': '你'}, {'start_ms': 700, 'end_ms': 1100, 'text': '好'}, {'start_ms': 1100, 'end_ms': 1300, 'text': '世'}, {'start_ms': 1300, 'end_ms': 1765, 'text': '界'}], 'wav_path': 'assets/hello_zh.wav'}
# {'uttid': 'hello_en', 'text': 'Hello speech.', 'sentences': [{'start_ms': 260, 'end_ms': 1820, 'text': 'Hello speech.', 'asr_confidence': 0.933, 'lang': 'en', 'lang_confidence': 0.993}], 'vad_segments_ms': [(260, 1820)], 'dur_s': 2.24, 'words': [{'start_ms': 400, 'end_ms': 960, 'text': 'hello'}, {'start_ms': 960, 'end_ms': 1666, 'text': 'speech'}], 'wav_path': 'assets/hello_en.wav'}
Note: FireRedASR2S code has only been tested on Linux Ubuntu 22.04. Behavior on other Linux distributions or Windows has not been tested.
Q: What audio format is supported?
16kHz 16-bit mono PCM wav. Use ffmpeg to convert other formats: ffmpeg -i <input_audio_path> -ar 16000 -ac 1 -acodec pcm_s16le -f wav <output_wav_path>
Q: What are the input length limitations of ASR models?
batch_size to 1 to avoid the repetition issue.Metrics: Character Error Rate (CER%) for Chinese and Word Error Rate (WER%) for English. Lower is better.
We evaluate FireRedASR2 on 24 public test sets covering Mandarin, 20+ Chinese dialects/accents, and singing.
Note: FRASR2=FireRedASR2, ws=WenetSpeech, md=MagicData, conv=Conversational, daily=Daily-use.
| ID | Testset\CER\Model | FRASR2-LLM | FRASR2-AED | Doubao-ASR | Qwen3-ASR | Fun-ASR |
|---|---|---|---|---|---|---|
| Avg | All(1-24) | 9.67 | 9.80 | 12.98 | 10.12 | 10.92 |
| Avg | Mandarin(1-4) | 2.89 | 3.05 | 3.69 | 3.76 | 4.16 |
| Avg | Dialect(5-23) | 11.55 | 11.67 | 15.39 | 11.85 | 12.76 |
| 1 | aishell1 | 0.64 | 0.57 | 1.52 | 1.48 | 1.64 |
| 2 | aishell2 | 2.15 | 2.51 | 2.77 | 2.71 | 2.38 |
| 3 | ws-net | 4.44 | 4.57 | 5.73 | 4.97 | 6.85 |
| 4 | ws-meeting | 4.32 | 4.53 | 4.74 | 5.88 | 5.78 |
| 5 | kespeech | 3.08 | 3.60 | 5.38 | 5.10 | 5.36 |
| 6 | ws-yue-short | 5.14 | 5.15 | 10.51 | 5.82 | 7.34 |
| 7 | ws-yue-long | 8.71 | 8.54 | 11.39 | 8.85 | 10.14 |
| 8 | ws-chuan-easy | 10.90 | 10.60 | 11.33 | 11.99 | 12.46 |
| 9 | ws-chuan-hard | 20.71 | 21.35 | 20.77 | 21.63 | 22.49 |
| 10 | md-heavy | 7.42 | 7.43 | 7.69 | 8.02 | 9.13 |
| 11 | md-yue-conv | 12.23 | 11.66 | 26.25 | 9.76 | 33.71 |
| 12 | md-yue-daily | 3.61 | 3.35 | 12.82 | 3.66 | 2.69 |
| 13 | md-yue-vehicle | 4.50 | 4.83 | 8.66 | 4.28 | 6.00 |
| 14 | md-chuan-conv | 13.18 | 13.07 | 11.77 | 14.35 | 14.01 |
| 15 | md-chuan-daily | 4.90 | 5.17 | 3.90 | 4.93 | 3.98 |
| 16 | md-shanghai-conv | 28.70 | 27.02 | 45.15 | 29.77 | 25.49 |
| 17 | md-shanghai-daily | 24.94 | 24.18 | 44.06 | 23.93 | 12.55 |
| 18 | md-wu | 7.15 | 7.14 | 7.70 | 7.57 | 10.63 |
| 19 | md-zhengzhou-conv | 10.20 | 10.65 | 9.83 | 9.55 | 10.85 |
| 20 | md-zhengzhou-daily | 5.80 | 6.26 | 5.77 | 5.88 | 6.29 |
| 21 | md-wuhan | 9.60 | 10.81 | 9.94 | 10.22 | 4.34 |
| 22 | md-tianjin | 15.45 | 15.30 | 15.79 | 16.16 | 19.27 |
| 23 | md-changsha | 23.18 | 25.64 | 23.76 | 23.70 | 25.66 |
| 24 | opencpop | 1.12 | 1.17 | 4.36 | 2.57 | 3.05 |
FireRedVAD achieves SOTA performance, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD.
| Metric\Model | FireRedVAD | Silero-VAD | TEN-VAD | FunASR-VAD | WebRTC-VAD |
|---|---|---|---|---|---|
| AUC-ROC↑ | 99.60 | 97.99 | 97.81 | - | - |
| F1 score↑ | 97.57 | 95.95 | 95.19 | 90.91 | 52.30 |
| False Alarm Rate↓ | 2.69 | 9.41 | 15.47 | 44.03 | 2.83 |
| Miss Rate↓ | 3.62 | 3.95 | 2.95 | 0.42 | 64.15 |
FLEURS-VAD-102: We randomly selected ~100 audio files per language from FLEURS test set, resulting in 9,443 audio files with manually annotated binary VAD labels (speech=1, silence=0). This VAD testset will be open sourced (coming soon).
Note: FunASR-VAD achieves low Miss Rate but at the cost of high False Alarm Rate (44.03%), indicating over-prediction of speech segments.
We evaluate FireRedLID on multilingual and Chinese dialect benchmarks.
FireRedLID achieves SOTA performance, outperforming Whisper, SpeechBrain-LID, and Dolphin.
| Testset\Model | Languages | FireRedLID | Whisper | SpeechBrain | Dolphin |
|---|---|---|---|---|---|
| FLEURS test | 82 languages | 97.18 | 79.41 | 92.91 | - |
| CommonVoice test | 74 languages | 92.07 | 80.81 | 78.75 | - |
| KeSpeech + MagicData | 20+ Chinese dialects/accents | 88.47 | - | - | 69.01 |
We evaluate FireRedPunc on multi-domain Chinese and English benchmarks.
FireRedPunc achieves SOTA performance, outperforming FunASR-Punc (CT-Transformer).
| Testset\Model | #Sentences | FireRedPunc | FunASR-Punc |
|---|---|---|---|
| Multi-domain Chinese | 88,644 | 82.84 / 83.08 / 82.96 | 77.27 / 74.03 / 75.62 |
| Multi-domain English | 28,641 | 78.40 / 71.57 / 74.83 | 55.79 / 45.15 / 49.91 |
| Average F1 Score | - | 78.90 | 62.77 |
Thanks to the following open-source works:
@article{xu2026fireredasr2s,
title={FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System},
author={Xu, Kaituo and Jia, Yan and Huang, Kai and Chen, Junjie and Li, Wenpeng and Liu, Kun and Xie, Feng-Long and Tang, Xu and Hu, Yao},
journal={arXiv preprint arXiv:2603.10420},
year={2026}
}
FireRedTeam/FireRedPunc is a model on Hugging Face by FireRedTeam. Automatic speech recognition model, used with transformers.
It declares the apache-2.0 license on Hugging Face.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on Hugging Face was on 2026-03-13. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
Automatic speech recognition model, used with transformers.
Sentence similarity model, used with sentence-transformers.
Automatic speech recognition model, used with nemo.
Automatic speech recognition model, used with pyannote-audio.

Token classification model, used with transformers.
Image to image model, used with diffusers.
Image to image model, used with diffusers.