A seguirPróximo guia
Codecs de áudio neural
IA de áudio
GUIA de IA de áudio
Mimi is Kyutai’s neural audio codec used with Moshi.
Ouça este guiaNarrado por IA · ~2 min
It converts 24 kHz audio into discrete representations at 12.5 frames per second, enabling speech models to predict and decode audio tokens. The paper describes a semantic codebook distilled from WavLM and acoustic codebooks for reconstruction; the specific rates and latency belong to the published configuration.
The Moshi paper introduces Mimi as a streaming neural codec operating on 24 kHz audio with a 12.5 Hz token frame rate and 1.1 kbps bandwidth in the reported setup. The encoder produces a semantic codebook distilled from WavLM and acoustic codebooks that support reconstruction, using split residual vector quantization. Causal masking in the encoder/decoder Transformers supports streaming inference. The paper reports an 80 ms frame size; it should not be read as a guaranteed end-to-end conversational response time. Mimi supplies audio tokens for Moshi’s audio-text modeling, but codec tokens are not ordinary text tokens.
Use a codec to represent incoming speech as discrete tokens that a speech-text model can process.
Decode predicted audio tokens back into a waveform for speech output.
Compare token rate and bitrate when assessing autoregressive sequence length and codec fidelity.
Inspect the split semantic/acoustic codebooks described in the Moshi report.
Neural codecs provide one interface for speech models to encode and generate audio. Future work may adjust token rates, codebook allocation, and streaming latency; each trade-off must be evaluated for the intended audio quality, hardware, and dialogue task.
Boletim informativo gratuito
Três histórias verificadas de IA a cada manhã de dia útil, escritas em linguagem simples. Gratuito para sempre, sem anúncios.
Um e-mail a cada dia útil. Cancele a inscrição com um clique. Nunca vendemos ou compartilhamos seu endereço.
Teste você mesmo
Feedback instantâneo sobre cada resposta e um certificado compartilhável com um ID verificável assim que você concluir um curso.
Apoie a educação gratuita em IA. O AI Understanding é uma organização sem fins lucrativos 501(c)(3) — sem anúncios, sem paywall, nunca. Faça uma doação
Mimi is Kyutai’s neural audio codec used with Moshi. It converts 24 kHz audio into discrete representations at 12.5 frames per second, enabling speech models to predict and decode audio tokens. The paper describes a semantic codebook distilled from WavLM and acoustic codebooks for reconstruction; the specific rates and latency belong to the published configuration.
Mimi e Moshi foram lançados em 2024 pelo laboratório de pesquisa francês Kyutai, que abriu o código-fonte de ambos.
Mimi comprime áudio de 24 kHz para apenas cerca de 12,5 tokens por segundo a aproximadamente 1,1 kbps.
The Moshi paper describes distilling WavLM representations into Mimi’s semantic codebook; it does not claim that this codebook is a literal transcript or exact speaker-identity record.
Mimi’s causal encoder/decoder can process frames as audio arrives rather than requiring the full utterance. The paper’s 80 ms figure is a codec frame interval, not a guaranteed end-to-end dialogue latency.
Mimi usa quantização vetorial residual, empilhando vários livros de códigos para que cada um adicione detalhes mais sutis ao anterior.
Continue aprendendo
Mais guias escolhidos para este tópico
A seguirPróximo guia
Codecs de áudio neural
IA de áudio