Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
SenseVoiceSmall is Alibaba's
multi-task encoder-only ASR
: one forward pass through a 70-block SANM encoder emits the full transcript
plus
the spoken language ID, emotion, and audio-event tags through a single CTC head. Non-autoregressive design →
15× faster than Whisper-Large
(70 ms for 10 s of audio in upstream's measurements).
70-block SenseVoiceEncoderSmall
(1 entry block @ 560→512 + 49 main blocks + 20 tp blocks, all 512-dim, 4 heads, FSMN k=11 depthwise convolution branch — the same encoder body Fun-ASR-Nano-2512 ships, just here paired with a CTC head instead of an LLM decoder)
4 query embeddings
(language / event / emotion / textnorm) prepended to the LFR fbank features so the encoder can emit rich annotations at those positions
CTC head
(
ctc.ctc_lo
, 25055 SentencePiece pieces)
50+ languages
with native LID (no whisper-tiny pre-step needed)
F16 only
ship: 0.47 GB. Q8_0/Q4_K pending.
What you get in the output
The transcript carries the 4-token rich-annotation prefix as readable
special tokens followed by the SentencePiece-detokenised transcript:
<|en|><|HAPPY|><|Speech|><|withitn|>And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.
<|zh|><|NEUTRAL|><|Speech|><|withitn|>开饭时间早上9点至下午5点。
<|yue|><|NEUTRAL|><|Speech|><|withitn|>呢几个字都表达唔到我想讲嘅意思。
<|ja|><|NEUTRAL|><|Speech|><|withitn|>うちの中学は弁当制で持っていけない場合は、50円の学校販売の パンを買う。
<|ko|><|NEUTRAL|><|Speech|><|withitn|>조금만 생각을 하면서 살면 훨씬 편할 거야.
crispasr-diff sensevoice
is 76/76 PASS, byte-identical
generated_text
,
on Alibaba's own example
zh.mp3
; 75/76 PASS on
samples/jfk.wav
with
the single difference being the emotion-tag argmax flipping between
<|ANGRY|>
and
<|EMO_UNKNOWN|>
(F16/op-order pushes that one slot
across a near-tied boundary; the transcript itself is byte-identical
in both runs). On Apple M1 Metal the runtime hits
15-22× realtime
.
These GGUF files are a quantised / repackaged distribution of the upstream weights and inherit the FunASR Model License v1.1. Please attribute Alibaba / FunAudioLLM in downstream products.
If you use this model, please also cite the upstream FunASR work.
See the
upstream model card
for the canonical citation.
Runs of cstr sensevoice-small-GGUF on huggingface.co
2.9K
Total runs
24
24-hour runs
79
3-day runs
304
7-day runs
1.2K
30-day runs
More Information About sensevoice-small-GGUF huggingface.co Model
sensevoice-small-GGUF huggingface.co is an AI model on huggingface.co that provides sensevoice-small-GGUF's model effect (), which can be used instantly with this cstr sensevoice-small-GGUF model. huggingface.co supports a free trial of the sensevoice-small-GGUF model, and also provides paid use of the sensevoice-small-GGUF. Support call sensevoice-small-GGUF model through api, including Node.js, Python, http.
sensevoice-small-GGUF huggingface.co is an online trial and call api platform, which integrates sensevoice-small-GGUF's modeling effects, including api services, and provides a free online trial of sensevoice-small-GGUF, you can try sensevoice-small-GGUF online for free by clicking the link below.
cstr sensevoice-small-GGUF online free url in huggingface.co:
sensevoice-small-GGUF is an open source model from GitHub that offers a free installation service, and any user can find sensevoice-small-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of sensevoice-small-GGUF install, users can directly use sensevoice-small-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
sensevoice-small-GGUF install url in huggingface.co: