SpeakoFlow/speakoflow-mini

zetlyn/models-gguf quantisation gguf SpeakoFlow/speakoflow-mini hf Qwen/Qwen3.5-0.8B known 2026-08-29

https://huggingface.co/SpeakoFlow/speakoflow-mini

Properties

authorSpeakoFlow
receipt
Source
GGUF quantisations
Its words
SpeakoFlow
Read by
field:author
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a92e8f744d2c3b3950a5113",
  "author": "SpeakoFlow",
  "cardData": {
    "base_model": "Qwen/Qwen3.5-0.8B",
    "base_model_relation": "finetune",
    "datasets": [
      "SpeakoFlow/dictation-cleanup-examples"
    ],
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "metrics": [
      "exact_match"
    ],
    "model-index": [
      {
        "name": "speakoflow-mini-0.8b",
        "results": [
          {
            "dataset": {
              "name": "SpeakoFlow dictation cleanup evaluation (held out)",
              "split": "test",
              "type": "dictation-cleanup-eval"
            },
            "metrics": [
              {
                "name": "Overall (mean of restraint and edit accuracy)",
                "type": "exact_match",
                "value": 70.7,
                "verified": false
              },
              {
                "name": "Restraint (already-correct text returned untouched)",
                "type": "exact_match",
                "value": 92.6,
                "verified": false
              },
              {
                "name": "Edit accuracy (transcripts needing a change)",
                "type": "exact_match",
                "value": 48.8,
                "verified": false
              },
              {
                "name": "Content damage (a spoken word lost, lower is better)",
                "type": "exact_match",
                "value": 10.7,
                "verified": false
              }
            ],
            "task": {
              "name": "Dictation cleanup",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "dictation",
      "transcript-cleanup",
      "asr-post-processing",
      "asr-error-correction",
      "speech-to-text",
      "post-asr-correction",
      "gguf",
      "llama.cpp",
      "qwen3.5",
      "local-llm",
      "cpu-inference"
    ]
  },
  "createdAt": "2026-08-29T14:13:11.000Z",
  "downloads": 13326,
  "gated": false,
  "id": "SpeakoFlow/speakoflow-mini",
  "lastModified": "2026-08-29T16:12:14.000Z",
  "likes": 12,
  "modelId": "SpeakoFlow/speakoflow-mini",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "835431771f72820251fe6c6b4b07f12b000e2647",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-BF16.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q4_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q5_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q6_K.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q8_0.gguf"
    },
    {
      "rfilename": "examples.jsonl"
    },
    {
      "rfilename": "figures/01-scorecard.png"
    },
    {
      "rfilename": "figures/02-ranking.png"
    },
    {
      "rfilename": "figures/03-two-axes.png"
    },
    {
      "rfilename": "figures/04-length.png"
    },
    {
      "rfilename": "figures/05-fine-tuning.png"
    },
    {
      "rfilename": "hf-banner-1600x500.png"
    }
  ],
  "tags": [
    "gguf",
    "dictation",
    "transcript-cleanup",
    "asr-post-processing",
    "asr-error-correction",
    "speech-to-text",
    "post-asr-correction",
    "llama.cpp",
    "qwen3.5",
    "local-llm",
    "cpu-inference",
    "text-generation",
    "en",
    "dataset:SpeakoFlow/dictation-cleanup-examples",
    "base_model:Qwen/Qwen3.5-0.8B",
    "base_model:finetune:Qwen/Qwen3.5-0.8B",
    "license:apache-2.0",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
baseQwen/Qwen3.5-0.8B
receipt
Source
GGUF quantisations
Its words
Qwen/Qwen3.5-0.8B
Read by
field:cardData.base_model[]
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a92e8f744d2c3b3950a5113",
  "author": "SpeakoFlow",
  "cardData": {
    "base_model": "Qwen/Qwen3.5-0.8B",
    "base_model_relation": "finetune",
    "datasets": [
      "SpeakoFlow/dictation-cleanup-examples"
    ],
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "metrics": [
      "exact_match"
    ],
    "model-index": [
      {
        "name": "speakoflow-mini-0.8b",
        "results": [
          {
            "dataset": {
              "name": "SpeakoFlow dictation cleanup evaluation (held out)",
              "split": "test",
              "type": "dictation-cleanup-eval"
            },
            "metrics": [
              {
                "name": "Overall (mean of restraint and edit accuracy)",
                "type": "exact_match",
                "value": 70.7,
                "verified": false
              },
              {
                "name": "Restraint (already-correct text returned untouched)",
                "type": "exact_match",
                "value": 92.6,
                "verified": false
              },
              {
                "name": "Edit accuracy (transcripts needing a change)",
                "type": "exact_match",
                "value": 48.8,
                "verified": false
              },
              {
                "name": "Content damage (a spoken word lost, lower is better)",
                "type": "exact_match",
                "value": 10.7,
                "verified": false
              }
            ],
            "task": {
              "name": "Dictation cleanup",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "dictation",
      "transcript-cleanup",
      "asr-post-processing",
      "asr-error-correction",
      "speech-to-text",
      "post-asr-correction",
      "gguf",
      "llama.cpp",
      "qwen3.5",
      "local-llm",
      "cpu-inference"
    ]
  },
  "createdAt": "2026-08-29T14:13:11.000Z",
  "downloads": 13326,
  "gated": false,
  "id": "SpeakoFlow/speakoflow-mini",
  "lastModified": "2026-08-29T16:12:14.000Z",
  "likes": 12,
  "modelId": "SpeakoFlow/speakoflow-mini",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "835431771f72820251fe6c6b4b07f12b000e2647",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-BF16.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q4_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q5_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q6_K.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q8_0.gguf"
    },
    {
      "rfilename": "examples.jsonl"
    },
    {
      "rfilename": "figures/01-scorecard.png"
    },
    {
      "rfilename": "figures/02-ranking.png"
    },
    {
      "rfilename": "figures/03-two-axes.png"
    },
    {
      "rfilename": "figures/04-length.png"
    },
    {
      "rfilename": "figures/05-fine-tuning.png"
    },
    {
      "rfilename": "hf-banner-1600x500.png"
    }
  ],
  "tags": [
    "gguf",
    "dictation",
    "transcript-cleanup",
    "asr-post-processing",
    "asr-error-correction",
    "speech-to-text",
    "post-asr-correction",
    "llama.cpp",
    "qwen3.5",
    "local-llm",
    "cpu-inference",
    "text-generation",
    "en",
    "dataset:SpeakoFlow/dictation-cleanup-examples",
    "base_model:Qwen/Qwen3.5-0.8B",
    "base_model:finetune:Qwen/Qwen3.5-0.8B",
    "license:apache-2.0",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
downloads13326
receipt
Source
GGUF quantisations
Its words
13326
Read by
field:downloads
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a92e8f744d2c3b3950a5113",
  "author": "SpeakoFlow",
  "cardData": {
    "base_model": "Qwen/Qwen3.5-0.8B",
    "base_model_relation": "finetune",
    "datasets": [
      "SpeakoFlow/dictation-cleanup-examples"
    ],
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "metrics": [
      "exact_match"
    ],
    "model-index": [
      {
        "name": "speakoflow-mini-0.8b",
        "results": [
          {
            "dataset": {
              "name": "SpeakoFlow dictation cleanup evaluation (held out)",
              "split": "test",
              "type": "dictation-cleanup-eval"
            },
            "metrics": [
              {
                "name": "Overall (mean of restraint and edit accuracy)",
                "type": "exact_match",
                "value": 70.7,
                "verified": false
              },
              {
                "name": "Restraint (already-correct text returned untouched)",
                "type": "exact_match",
                "value": 92.6,
                "verified": false
              },
              {
                "name": "Edit accuracy (transcripts needing a change)",
                "type": "exact_match",
                "value": 48.8,
                "verified": false
              },
              {
                "name": "Content damage (a spoken word lost, lower is better)",
                "type": "exact_match",
                "value": 10.7,
                "verified": false
              }
            ],
            "task": {
              "name": "Dictation cleanup",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "dictation",
      "transcript-cleanup",
      "asr-post-processing",
      "asr-error-correction",
      "speech-to-text",
      "post-asr-correction",
      "gguf",
      "llama.cpp",
      "qwen3.5",
      "local-llm",
      "cpu-inference"
    ]
  },
  "createdAt": "2026-08-29T14:13:11.000Z",
  "downloads": 13326,
  "gated": false,
  "id": "SpeakoFlow/speakoflow-mini",
  "lastModified": "2026-08-29T16:12:14.000Z",
  "likes": 12,
  "modelId": "SpeakoFlow/speakoflow-mini",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "835431771f72820251fe6c6b4b07f12b000e2647",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-BF16.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q4_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q5_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q6_K.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q8_0.gguf"
    },
    {
      "rfilename": "examples.jsonl"
    },
    {
      "rfilename": "figures/01-scorecard.png"
    },
    {
      "rfilename": "figures/02-ranking.png"
    },
    {
      "rfilename": "figures/03-two-axes.png"
    },
    {
      "rfilename": "figures/04-length.png"
    },
    {
      "rfilename": "figures/05-fine-tuning.png"
    },
    {
      "rfilename": "hf-banner-1600x500.png"
    }
  ],
  "tags": [
    "gguf",
    "dictation",
    "transcript-cleanup",
    "asr-post-processing",
    "asr-error-correction",
    "speech-to-text",
    "post-asr-correction",
    "llama.cpp",
    "qwen3.5",
    "local-llm",
    "cpu-inference",
    "text-generation",
    "en",
    "dataset:SpeakoFlow/dictation-cleanup-examples",
    "base_model:Qwen/Qwen3.5-0.8B",
    "base_model:finetune:Qwen/Qwen3.5-0.8B",
    "license:apache-2.0",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
licenceapache-2.0
receipt
Source
GGUF quantisations
Its words
apache-2.0
Read by
field:cardData.license
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a92e8f744d2c3b3950a5113",
  "author": "SpeakoFlow",
  "cardData": {
    "base_model": "Qwen/Qwen3.5-0.8B",
    "base_model_relation": "finetune",
    "datasets": [
      "SpeakoFlow/dictation-cleanup-examples"
    ],
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "metrics": [
      "exact_match"
    ],
    "model-index": [
      {
        "name": "speakoflow-mini-0.8b",
        "results": [
          {
            "dataset": {
              "name": "SpeakoFlow dictation cleanup evaluation (held out)",
              "split": "test",
              "type": "dictation-cleanup-eval"
            },
            "metrics": [
              {
                "name": "Overall (mean of restraint and edit accuracy)",
                "type": "exact_match",
                "value": 70.7,
                "verified": false
              },
              {
                "name": "Restraint (already-correct text returned untouched)",
                "type": "exact_match",
                "value": 92.6,
                "verified": false
              },
              {
                "name": "Edit accuracy (transcripts needing a change)",
                "type": "exact_match",
                "value": 48.8,
                "verified": false
              },
              {
                "name": "Content damage (a spoken word lost, lower is better)",
                "type": "exact_match",
                "value": 10.7,
                "verified": false
              }
            ],
            "task": {
              "name": "Dictation cleanup",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "dictation",
      "transcript-cleanup",
      "asr-post-processing",
      "asr-error-correction",
      "speech-to-text",
      "post-asr-correction",
      "gguf",
      "llama.cpp",
      "qwen3.5",
      "local-llm",
      "cpu-inference"
    ]
  },
  "createdAt": "2026-08-29T14:13:11.000Z",
  "downloads": 13326,
  "gated": false,
  "id": "SpeakoFlow/speakoflow-mini",
  "lastModified": "2026-08-29T16:12:14.000Z",
  "likes": 12,
  "modelId": "SpeakoFlow/speakoflow-mini",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "835431771f72820251fe6c6b4b07f12b000e2647",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-BF16.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q4_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q5_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q6_K.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q8_0.gguf"
    },
    {
      "rfilename": "examples.jsonl"
    },
    {
      "rfilename": "figures/01-scorecard.png"
    },
    {
      "rfilename": "figures/02-ranking.png"
    },
    {
      "rfilename": "figures/03-two-axes.png"
    },
    {
      "rfilename": "figures/04-length.png"
    },
    {
      "rfilename": "figures/05-fine-tuning.png"
    },
    {
      "rfilename": "hf-banner-1600x500.png"
    }
  ],
  "tags": [
    "gguf",
    "dictation",
    "transcript-cleanup",
    "asr-post-processing",
    "asr-error-correction",
    "speech-to-text",
    "post-asr-correction",
    "llama.cpp",
    "qwen3.5",
    "local-llm",
    "cpu-inference",
    "text-generation",
    "en",
    "dataset:SpeakoFlow/dictation-cleanup-examples",
    "base_model:Qwen/Qwen3.5-0.8B",
    "base_model:finetune:Qwen/Qwen3.5-0.8B",
    "license:apache-2.0",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
likes12
receipt
Source
GGUF quantisations
Its words
12
Read by
field:likes
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a92e8f744d2c3b3950a5113",
  "author": "SpeakoFlow",
  "cardData": {
    "base_model": "Qwen/Qwen3.5-0.8B",
    "base_model_relation": "finetune",
    "datasets": [
      "SpeakoFlow/dictation-cleanup-examples"
    ],
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "metrics": [
      "exact_match"
    ],
    "model-index": [
      {
        "name": "speakoflow-mini-0.8b",
        "results": [
          {
            "dataset": {
              "name": "SpeakoFlow dictation cleanup evaluation (held out)",
              "split": "test",
              "type": "dictation-cleanup-eval"
            },
            "metrics": [
              {
                "name": "Overall (mean of restraint and edit accuracy)",
                "type": "exact_match",
                "value": 70.7,
                "verified": false
              },
              {
                "name": "Restraint (already-correct text returned untouched)",
                "type": "exact_match",
                "value": 92.6,
                "verified": false
              },
              {
                "name": "Edit accuracy (transcripts needing a change)",
                "type": "exact_match",
                "value": 48.8,
                "verified": false
              },
              {
                "name": "Content damage (a spoken word lost, lower is better)",
                "type": "exact_match",
                "value": 10.7,
                "verified": false
              }
            ],
            "task": {
              "name": "Dictation cleanup",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "dictation",
      "transcript-cleanup",
      "asr-post-processing",
      "asr-error-correction",
      "speech-to-text",
      "post-asr-correction",
      "gguf",
      "llama.cpp",
      "qwen3.5",
      "local-llm",
      "cpu-inference"
    ]
  },
  "createdAt": "2026-08-29T14:13:11.000Z",
  "downloads": 13326,
  "gated": false,
  "id": "SpeakoFlow/speakoflow-mini",
  "lastModified": "2026-08-29T16:12:14.000Z",
  "likes": 12,
  "modelId": "SpeakoFlow/speakoflow-mini",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "835431771f72820251fe6c6b4b07f12b000e2647",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-BF16.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q4_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q5_K_M.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q6_K.gguf"
    },
    {
      "rfilename": "SpeakoFlow-Mini-0.8B-Q8_0.gguf"
    },
    {
      "rfilename": "examples.jsonl"
    },
    {
      "rfilename": "figures/01-scorecard.png"
    },
    {
      "rfilename": "figures/02-ranking.png"
    },
    {
      "rfilename": "figures/03-two-axes.png"
    },
    {
      "rfilename": "figures/04-length.png"
    },
    {
      "rfilename": "figures/05-fine-tuning.png"
    },
    {
      "rfilename": "hf-banner-1600x500.png"
    }
  ],
  "tags": [
    "gguf",
    "dictation",
    "transcript-cleanup",
    "asr-post-processing",
    "asr-error-correction",
    "speech-to-text",
    "post-asr-correction",
    "llama.cpp",
    "qwen3.5",
    "local-llm",
    "cpu-inference",
    "text-generation",
    "en",
    "dataset:SpeakoFlow/dictation-cleanup-examples",
    "base_model:Qwen/Qwen3.5-0.8B",
    "base_model:finetune:Qwen/Qwen3.5-0.8B",
    "license:apache-2.0",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}

Text

This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/SpeakoFlow/speakoflow-mini.