Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al from OpenAI. The original code repository can be found here. **Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were copied and pasted from the original model card.
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. The original code repository can be found here. **Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were copied and pasted from the original model card.
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. The original code repository can be found here. **Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were copied and pasted from the original model card.
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. The original code repository can be found here. **Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were copied and pasted from the original model card.
Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q8_0** is the recommended default — near-reference quality at a fraction of the footprint. Cohere Transcribe 03-2026 is Cohere and Cohere Labs' open release of a 2B-parameter automatic speech recognition model. It is a dedicated audio-in, text-out architecture with a Conformer-based acoustic encoder and a lightweight Transformer decoder, trained from scratch for transcription. The upstream model card lists support for 14 languages across English, European, APAC, and MENA coverage and reports Apache-2.0 licensing. This OpenASR repo repackages the original `CohereLabs/cohere-transcribe-03-2026` weights as `.oasr` packs that run natively in the OpenASR runtime with no Python at inference time. For most users the q8_0 build is the recommended default; q4_k is for tighter memory budgets and fp16 is for verification or maximum fidelity.
**FireRedTeam's LLM-backbone Mandarin-first bilingual ASR — 8B+ parameters engineered for state-of-the-art Chinese and dialect accuracy** Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q4_k** is the recommended default — near-reference quality at a fraction of the footprint.
**Joint transcription and speaker diarization in a single 0.9B-parameter model — know who said what, and when** Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q8_0** is the recommended default — near-reference quality at a fraction of the footprint.
**Multilingual speech recognition across 52 languages & dialects — the fast, lightweight Qwen3-ASR** Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q8_0** is the recommended default — near-reference quality at a fraction of the footprint.
**State-of-the-art multilingual speech recognition across 52 languages & dialects** Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. - 🏆 **SOTA among open-source ASR** — competitive with the strongest proprietary commercial APIs - 🌍 **52 languages & dialects** — 30 languages plus 22 Chinese dialects, with spoken-language identification - 🎧 **Robust on hard audio** — clean speech, singing voice, and songs over background music - 🦀 **Native in OpenASR** — `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU
**Word-level forced alignment for OpenASR transcripts -- a non-autoregressive Qwen3 audio+text model that refines per-word timestamps** A capability-pack support model for the **OpenASR** runtime — pure-Rust inference, **no Python at inference time**. Not a standalone transcription model: it augments another OpenASR ASR model's own decode path. Qwen3-ForcedAligner-0.6B is a **word-level forced-alignment** model from **Qwen**, sharing its audio-encoder + LM `thinker` tensor layout byte-for-byte with **Qwen3-ASR** (same `Qwen3ASRForConditionalGeneration` architecture). The only structural difference is the final head: instead of a tied vocabulary `lm_head`, it uses an independent `Linear(hidden_size, 5000)` classification head over 80ms-wide timestamp bins. Given a transcript's text and its source audio, it runs a single non-autoregressive forward pass and reads off word-boundary timestamps at argmax ` ` positions -- refining a model family's own (typically decode-time-approximate) per-word timestamps. This OpenASR repo repackages the weights as `.oasr` packs that run natively in the OpenASR runtime -- no Python at inference, all decoding local. OpenASR recommends the validated **q4_k** tier and also ships **q8_0** and an **fp16** full-precision reference tier. The q4_k label is the catalog's unified product name, not a claim that every matrix uses Q4_K: the audio encoder, token embedding, and timestamp head remain Q8_0, and pack verification replays the exact per-tensor policy. Q3 and legacy all-Q4 packs are rejected because small logit perturbations can move a word boundary across multiple 80ms bins.
MOSS-Audio is an open-source **audio understanding model** from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute. It performs unified modeling over complex real-world audio, supporting **speech understanding, environmental sound understanding, music understanding, audio captioning, time-aware QA, and complex reasoning**. In this release, we provide **four models**: **MOSS-Audio-4B-Instruct**, **MOSS-Audio-4B-Thinking**, **MOSS-Audio-8B-Instruct**, and **MOSS-Audio-8B-Thinking**. The Instruct variants are optimized for direct instruction following, while the Thinking variants provide stronger chain-of-thought reasoning capabilities. Understanding audio requires more than simply transcribing words — it demands the ability to perceive acoustic cues, recognize speakers and emotions, interpret environmental sounds, reason over temporal context, and handle complex multi-step inference. **MOSS-Audio** is built to unify these capabilities within a single model. MOSS-Audio follows a modular design comprising three components: an audio encoder, a modality adapter, and a large language model. Raw audio is first encoded by **MOSS-Audio-Encoder** into continuous temporal representations at **12.5 Hz**, which are then projected into the language model's embedding space through the adapter and finally consumed by the LLM for auto-regressive text generation.
