Skip to main content

Qwen3 ASR model for fasr

Project description

fasr-asr-qwen3asr

英文文档地址: README_EN.md

Qwen3-ASR 语音识别插件,使用内置的 Qwen3-ASR vLLM 后端。同一个模型实例支持离线批量识别和累计式流式识别。

安装

pip install fasr-asr-qwen3asr

注册模型

注册名 size 选择的类 适用场景
qwen3asr Qwen3ASRSmallQwen3ASRLarge GPU ASR,无词级时间戳

size="small" 使用 Qwen/Qwen3-ASR-0.6Bsize="large" 使用 Qwen/Qwen3-ASR-1.7B

流水线使用

from fasr import AudioPipeline

pipeline = (
    AudioPipeline()
    .add_pipe("detector", model="fsmn")
    .add_pipe(
        "recognizer",
        model="qwen3asr",
        size="small",
        gpu_memory_utilization=0.7,
        max_new_tokens=2048,
    )
    .add_pipe("sentencizer", model="ct_transformer")
)
目标 写法 效果
降低显存 size="small" 使用 0.6B checkpoint
提高能力 size="large" 使用 1.7B checkpoint,需要更多显存
给 GPU 留余量 gpu_memory_utilization=0.6 vLLM 预留更少显存
长文本输出 max_new_tokens=4096 或更高 允许生成更长文本
偏置专有名词 hotwords=[...] 通过 Qwen3-ASR 官方 context 通道提供热词
固定语言 language="zh" 使用固定语言提示

Confection 配置

[asr_model]
@asr_models = "qwen3asr"
size = "small"
gpu_memory_utilization = 0.7
max_new_tokens = 2048
language = "Chinese"
hotwords = ["fasr", "Qwen3-ASR"]

放在流水线里:

[pipeline]
@pipelines = "AudioPipeline.v1"
pipe_order = ["recognizer"]

[pipeline.pipes]

[pipeline.pipes.recognizer]
@pipes = "thread_pipe"
batch_size = 1

[pipeline.pipes.recognizer.component]
@components = "recognizer"

[pipeline.pipes.recognizer.component.model]
@asr_models = "qwen3asr"
size = "small"
gpu_memory_utilization = 0.7
max_new_tokens = 2048
language = "Chinese"
hotwords = ["fasr", "Qwen3-ASR"]

单独使用

from fasr.config import registry

model = registry.asr_models.get("qwen3asr")(
    size="small",
    gpu_memory_utilization=0.7,
)

spans = model.transcribe(audio_spans)
for span in spans:
    print(span.text)

流式模式返回累计文本,上层应覆盖显示最新文本,不要拼接 delta:

model = registry.asr_models.get("qwen3asr")(
    size="small",
    chunk_size_ms=2000,
    language="zh",
)

for chunk in audio_chunks:
    span = model.push_chunk(chunk)
    if span is not None:
        print(span.text)

参数

参数 类型 / 范围 默认值 调高 / 开启时 调低 / 关闭时 什么时候改
size "small""large" "small" "large" 能力更强,显存更高 "small" 更省资源 精度或资源预算变化
gpu_memory_utilization float(0, 1] 0.8 vLLM 预留更多显存 给其它进程留更多显存 vLLM OOM 或显存未充分使用
max_new_tokens int >= 1 4096 允许更长输出 计算和显存更省 文本截断或资源紧张
max_inference_batch_size int-1 或正数 -1 -1 交给后端 更低峰值显存 批量推理 OOM
max_model_len intNone None 更长 prompt+输出上下文 更省内存 长上下文或 OOM
language strNone None 固定语言提示 自动语言行为 已知语言
hotwords list[str] [] 更强热词偏置 更少 prompt 偏置 专有名词漏识别
chunk_size_ms intNone None 流式解码更少,输出更晚 更实时,开销更高 流式延迟/吞吐调优

输出

  • 离线模式写入 span.raw_text
  • 流式模式返回累计 AudioSpan(raw_text=...)
  • 当前插件不返回词级或字级时间戳。

依赖

  • fasr
  • transformers == 4.57.6
  • huggingface-hub >= 0.34.0, < 1.0
  • vllm == 0.14.0
  • accelerate == 1.12.0
  • librosa
  • soundfile
  • Python 3.10-3.12

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fasr_asr_qwen3asr-0.5.8.tar.gz (119.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fasr_asr_qwen3asr-0.5.8-py3-none-any.whl (122.1 kB view details)

Uploaded Python 3

File details

Details for the file fasr_asr_qwen3asr-0.5.8.tar.gz.

File metadata

  • Download URL: fasr_asr_qwen3asr-0.5.8.tar.gz
  • Upload date:
  • Size: 119.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.17 {"installer":{"name":"uv","version":"0.9.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for fasr_asr_qwen3asr-0.5.8.tar.gz
Algorithm Hash digest
SHA256 7ad3b09cfcef77759cd10860acfc9bb7243f0f32cee7a08a8d52baa867725b50
MD5 ebc338b1f15647ba6434c81dde142153
BLAKE2b-256 f08b2e799575eff3217d0deec0d654fcba81baeff27be8de4007f88a066513f5

See more details on using hashes here.

File details

Details for the file fasr_asr_qwen3asr-0.5.8-py3-none-any.whl.

File metadata

  • Download URL: fasr_asr_qwen3asr-0.5.8-py3-none-any.whl
  • Upload date:
  • Size: 122.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.17 {"installer":{"name":"uv","version":"0.9.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for fasr_asr_qwen3asr-0.5.8-py3-none-any.whl
Algorithm Hash digest
SHA256 0dd086fd1a9bf8bd987c30b1d5454c1bde12013fa063234c549934f0c9364931
MD5 c8133da144fd1f11547350cf39fbb85f
BLAKE2b-256 314e84010ed06657c9b8787d159c0a7018ff2d71c2e44cf21730519f079c156b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page