librispeech-en-whispercpp-medium-batch

Audio

15 utterances · 145.195s total · 16000 Hz

Integrity

sha256: b52ce70b5c40664c6f025ab4924588f571099741d02046dfb0c39547b9494d69

Full manifest

{
  "id": "librispeech-en-whispercpp-medium-batch",
  "version": "1.0.0",
  "sha256": "b52ce70b5c40664c6f025ab4924588f571099741d02046dfb0c39547b9494d69",
  "profile_id": "whispercpp-medium-en-batch",
  "visibility": "open",
  "license": "CC-BY-4.0",
  "audio": {
    "count": 15,
    "total_duration_s": 145.195,
    "sample_rate_hz": 16000,
    "manifest_sha256": "6b9cdcf81a565496b7d4ef4881b035d98593eb941e61d87780591f0aba5852d9",
    "source": {
      "type": "librispeech",
      "params": {
        "speaker": "1272",
        "chapter": "128104",
        "split": "dev-clean"
      },
      "fetch_instructions": "Identical audio to librispeech-en-batch — auto-fetched the same way. Manual fallback: run `python scripts/fetch_librispeech_subset.py --speaker 1272 --chapter 128104`, then pass `--audio-dir packs/librispeech-en-batch/audio` to `goesb run`."
    }
  },
  "metadata": {
    "language": "en-US",
    "recording_environment": "studio",
    "speech_style": "read",
    "transcription_style": "verbatim",
    "tags": [
      "librispeech",
      "en"
    ]
  }
}