Module: Cohere::Transcribe::Audio::Decoder

Defined in:
lib/cohere/transcribe/audio/decoder.rb

Constant Summary collapse

SFM_READ =
0x10
SRC_SINC_FASTEST =
2
BACKENDS =
%w[auto ffmpeg torchcodec librosa libsndfile].freeze

Class Method Summary collapse

Class Method Details

.decode(path, backend: "auto", sample_rate: SAMPLE_RATE, max_decoded_bytes: 4 * (1024**3)) ⇒ Object

Raises:

  • (ArgumentError)


150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
# File 'lib/cohere/transcribe/audio/decoder.rb', line 150

def decode(path, backend: "auto", sample_rate: SAMPLE_RATE, max_decoded_bytes: 4 * (1024**3))
  requested = backend
  unless requested.is_a?(String) && BACKENDS.include?(requested)
    raise ArgumentError, "Unsupported audio backend: #{backend.inspect}"
  end
  raise ArgumentError, "sample_rate must be a positive integer" unless sample_rate.is_a?(Integer) && sample_rate.positive?
  unless max_decoded_bytes.nil? || (max_decoded_bytes.is_a?(Integer) && max_decoded_bytes.positive?)
    raise ArgumentError, "max_decoded_bytes must be a positive integer or nil"
  end

  source = Pathname(path).expand_path
  raise TranscriptionInputError, "Input does not exist: #{source}" unless source.exist?
  raise TranscriptionInputError, "Input is not a regular file: #{source}" unless source.file?

  native_ffmpeg_available = %w[auto librosa].include?(requested) && FFmpegNative.available?
  use_ffmpeg = requested == "ffmpeg" || requested == "torchcodec" ||
               (%w[auto librosa].include?(requested) && native_ffmpeg_available)
  if use_ffmpeg
    samples = FFmpegNative.decode(
      source,
      sample_rate: sample_rate,
      max_decoded_bytes: max_decoded_bytes
    )
    validate_finite!(samples)
    return Decoded.new(
      samples: samples.freeze,
      sample_rate: sample_rate,
      backend: "ffmpeg",
      fallback_reason: if %w[torchcodec librosa].include?(requested)
                         "Ruby #{requested} compatibility mode uses FFmpeg through the native C ABI"
                       end
    )
  end

  unless SoundFileABI::AVAILABLE
    sound_file_error = if SoundFileABI.const_defined?(:LOAD_ERROR, false)
                         SoundFileABI::LOAD_ERROR.message
                       else
                         "not found"
                       end
    if requested == "auto"
      raise TranscriptionRuntimeError,
            "Automatic audio decoding requires the native FFmpeg adapter or libsndfile " \
            "(FFmpeg: #{FFmpegNative.diagnostic}; libsndfile: #{sound_file_error})"
    end
    raise TranscriptionRuntimeError, "libsndfile is required for native audio decoding: #{sound_file_error}"
  end

  info = SoundFileABI::SFInfo.malloc
  handle = SoundFileABI.sf_open(source.to_s, SFM_READ, info.to_ptr)
  raise TranscriptionRuntimeError, "Cannot decode #{source}: #{SoundFileABI.sf_strerror(handle)}" if handle.null?

  begin
    frames = Integer(info.frames)
    channels = Integer(info.channels)
    source_rate = Integer(info.samplerate)
    unless frames >= 0 && channels.positive? && source_rate.positive?
      raise TranscriptionRuntimeError, "Decoder returned invalid audio metadata for #{source}"
    end

    input_bytes = frames * channels * Fiddle::SIZEOF_FLOAT
    output_frames = (frames * sample_rate.fdiv(source_rate)).ceil + 64
    projected_bytes = [input_bytes, output_frames * Fiddle::SIZEOF_FLOAT].max
    if max_decoded_bytes && projected_bytes > max_decoded_bytes
      raise TranscriptionRuntimeError,
            "Decoded audio exceeds the configured memory limit for #{source} " \
            "(#{projected_bytes} > #{max_decoded_bytes} bytes)"
    end

    raw = Fiddle::Pointer.malloc([input_bytes, 1].max, Fiddle::RUBY_FREE)
    read_frames = SoundFileABI.sf_readf_float(handle, raw, frames)
    raise TranscriptionRuntimeError, "Cannot decode #{source}: #{SoundFileABI.sf_strerror(handle)}" if read_frames.negative?
    raise TranscriptionRuntimeError, "Decoder returned more frames than allocated for #{source}" if read_frames > frames

    frames = read_frames
    begin
      require "numo/narray"
    rescue LoadError => e
      raise TranscriptionRuntimeError, "numo-narray is required for decoded audio: #{e.message}"
    end
    interleaved = if frames.zero?
                    nil
                  else
                    Numo::SFloat.from_binary(raw[0, frames * channels * Fiddle::SIZEOF_FLOAT])
                  end
    mono = if frames.zero?
             Numo::SFloat.zeros(0)
           elsif channels == 1
             interleaved
           else
             interleaved.reshape(frames, channels).mean(1).cast_to(Numo::SFloat)
           end
    samples = source_rate == sample_rate ? mono : resample(mono, source_rate, sample_rate, max_decoded_bytes)
    validate_finite!(samples)
    Decoded.new(
      samples: samples.freeze,
      sample_rate: sample_rate,
      backend: "libsndfile",
      fallback_reason: if %w[auto libsndfile].include?(requested)
                         nil
                       else
                         "Ruby #{requested} compatibility mode uses the native libsndfile ABI"
                       end
    )
  ensure
    SoundFileABI.sf_close(handle)
  end
end

.probe_duration(path) ⇒ Object

Best-effort metadata probe used for public skipped-result parity. It may inspect container headers and demuxer probe packets but never launches ffprobe or materializes decoded PCM in Ruby.



124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# File 'lib/cohere/transcribe/audio/decoder.rb', line 124

def probe_duration(path)
  source = Pathname(path).expand_path
  return nil unless source.file?

  if FFmpegNative.available?
    duration = FFmpegNative.duration(source)
    return duration if duration
  end
  return nil unless SoundFileABI::AVAILABLE

  info = SoundFileABI::SFInfo.malloc
  handle = SoundFileABI.sf_open(source.to_s, SFM_READ, info.to_ptr)
  return nil if handle.null?

  frames = Integer(info.frames)
  sample_rate = Integer(info.samplerate)
  return nil unless frames >= 0 && sample_rate.positive?

  seconds = frames.fdiv(sample_rate)
  seconds if seconds.finite? && seconds >= 0.0
rescue Fiddle::DLError, SystemCallError, TranscriptionRuntimeError
  nil
ensure
  SoundFileABI.sf_close(handle) if defined?(handle) && handle && !handle.null?
end

.resample(samples, source_rate, target_rate, max_decoded_bytes) ⇒ Object



259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
# File 'lib/cohere/transcribe/audio/decoder.rb', line 259

def resample(samples, source_rate, target_rate, max_decoded_bytes)
  unless source_rate.is_a?(Integer) && source_rate.positive? &&
         target_rate.is_a?(Integer) && target_rate.positive?
    raise ArgumentError, "source_rate and target_rate must be positive integers"
  end
  return Numo::SFloat.zeros(0) if samples.empty?

  unless SampleRateABI::AVAILABLE
    error = SampleRateABI.const_defined?(:LOAD_ERROR, false) ? SampleRateABI::LOAD_ERROR.message : "not found"
    raise TranscriptionRuntimeError, "libsamplerate is required to resample audio: #{error}"
  end
  ratio = target_rate.fdiv(source_rate)
  output_capacity = (samples.length * ratio).ceil + 64
  bytes = output_capacity * Fiddle::SIZEOF_FLOAT
  if max_decoded_bytes && bytes > max_decoded_bytes
    raise TranscriptionRuntimeError, "Resampled audio exceeds the configured memory limit"
  end

  input_string = samples.to_binary
  input_pointer = Fiddle::Pointer[input_string]
  output_pointer = Fiddle::Pointer.malloc([bytes, 1].max, Fiddle::RUBY_FREE)
  data = SampleRateABI::SRCData.malloc
  data.data_in = input_pointer
  data.data_out = output_pointer
  data.input_frames = samples.length
  data.output_frames = output_capacity
  data.input_frames_used = 0
  data.output_frames_gen = 0
  data.end_of_input = 1
  data.src_ratio = ratio
  error_code = SampleRateABI.src_simple(data.to_ptr, SRC_SINC_FASTEST, 1)
  raise TranscriptionRuntimeError, "Audio resampling failed: #{SampleRateABI.src_strerror(error_code)}" unless error_code.zero?

  generated = Integer(data.output_frames_gen)
  consumed = Integer(data.input_frames_used)
  unless consumed == samples.length && generated.between?(0, output_capacity)
    raise TranscriptionRuntimeError,
          "Audio resampling returned invalid frame counts " \
          "(consumed #{consumed}/#{samples.length}, generated #{generated}/#{output_capacity})"
  end
  Numo::SFloat.from_binary(output_pointer[0, generated * Fiddle::SIZEOF_FLOAT])
end